Search Results for author: Bo Liu

Found 222 papers, 67 papers with code

Basis Construction from Power Series Expansions of Value Functions

no code implementations NeurIPS 2010 Sridhar Mahadevan, Bo Liu

This paper explores links between basis construction methods in Markov decision processes and power series expansions of value functions.

Unity

Bayesian Analysis for miRNA and mRNA Interactions Using Expression Data

no code implementations12 Oct 2012 Mingjun Zhong, Rong Liu, Bo Liu

Compared to the point estimate algorithms, which only provide single estimates for those parameters, the Bayesian methods are more meaningful and provide credible intervals, which take into account the uncertainty of the inferred interactions of the miRNA and mRNA.

regression Specificity

Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces

no code implementations26 May 2014 Sridhar Mahadevan, Bo Liu, Philip Thomas, Will Dabney, Steve Giguere, Nicholas Jacek, Ian Gemp, Ji Liu

In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified "safety" guarantees, and remains in a stable region of the parameter space (iii) how to design "off-policy" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate the study of reinforcement learning into the rich theory of stochastic optimization.

Decision Making reinforcement-learning +2

Heterogeneous Metric Learning with Content-based Regularization for Software Artifact Retrieval

no code implementations25 Sep 2014 Liang Wu, Hui Xiong, Liang Du, Bo Liu, Guandong Xu, Yong Ge, Yanjie Fu, Yuanchun Zhou, Jianhui Li

Specifically, this method can capture both the inherent information in the source codes and the semantic information hidden in the comments, descriptions, and identifiers of the source codes.

Information Retrieval Metric Learning +1

Bayesian Model Adaptation for Crowd Counts

no code implementations ICCV 2015 Bo Liu, Nuno Vasconcelos

A large video dataset for the evaluation of adaptation approaches to crowd counting is also introduced.

Crowd Counting Gaussian Processes +1

Regression-based Hypergraph Learning for Image Clustering and Classification

no code implementations14 Mar 2016 Sheng Huang, Dan Yang, Bo Liu, Xiaohong Zhang

Moreover, we plug RH into two conventional hypergraph learning frameworks, namely hypergraph spectral clustering and hypergraph transduction, to present Regression-based Hypergraph Spectral Clustering (RHSC) and Regression-based Hypergraph Transduction (RHT) models for addressing the image clustering and classification issues.

Classification Clustering +3

Neural Clinical Paraphrase Generation with Attention

no code implementations WS 2016 Sadid A. Hasan, Bo Liu, Joey Liu, Ashequl Qadir, Kathy Lee, Vivek Datla, Aaditya Prakash, Oladimeji Farri

Paraphrase generation is important in various applications such as search, summarization, and question answering due to its ability to generate textual alternatives while keeping the overall meaning intact.

Document Summarization Information Retrieval +5

O$^2$TD: (Near)-Optimal Off-Policy TD Learning

no code implementations17 Apr 2017 Bo Liu, Daoming Lyu, Wen Dong, Saad Biaz

Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w. r. t approximating the true value function $V$.

Feature Space Transfer for Data Augmentation

no code implementations CVPR 2018 Bo Liu, Xudong Wang, Mandar Dixit, Roland Kwitt, Nuno Vasconcelos

A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose.

Data Augmentation Object +2

Privacy Preservation in Location-Based Services: A Novel Metric and Attack Model

no code implementations16 May 2018 Sina Shaham, Ming Ding, Bo Liu, Zihuai Lin, Jun Li

In this paper, we incorporate a new type of side information based on consecutive location changes of users and propose a new metric called transition-entropy to investigate the location privacy preservation, followed by two algorithms to improve the transition-entropy for a given dummy generation algorithm.

Constrained-size Tensorflow Models for YouTube-8M Video Understanding Challenge

2 code implementations21 Aug 2018 Tianqi Liu, Bo Liu

This paper presents our 7th place solution to the second YouTube-8M video understanding competition which challenges participates to build a constrained-size model to classify millions of YouTube videos into thousands of classes.

Video Understanding

A Block Coordinate Ascent Algorithm for Mean-Variance Optimization

no code implementations NeurIPS 2018 Bo Liu, Tengyang Xie, Yangyang Xu, Mohammad Ghavamzadeh, Yin-Lam Chow, Daoming Lyu, Daesub Yoon

Risk management in dynamic decision problems is a primary concern in many fields, including financial investment, autonomous driving, and healthcare.

Autonomous Driving Management

SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning

no code implementations31 Oct 2018 Daoming Lyu, Fangkai Yang, Bo Liu, Steven Gustafson

The three components cross-fertilize each other and eventually converge to an optimal symbolic plan along with the learned subtasks, bringing together the advantages of long-term planning capability with symbolic knowledge and end-to-end reinforcement learning directly from a high-dimensional sensory input.

Decision Making reinforcement-learning +2

Dantzig Selector with an Approximately Optimal Denoising Matrix and its Application to Reinforcement Learning

no code implementations2 Nov 2018 Bo Liu, Luwan Zhang, Ji Liu

To make the problem computationally tractable, we propose a novel algorithm, termed as Optimal Denoising Dantzig Selector (ODDS), to approximately estimate the optimal denoising matrix.

Denoising feature selection +2

QUOTA: The Quantile Option Architecture for Reinforcement Learning

3 code implementations5 Nov 2018 Shangtong Zhang, Borislav Mavrin, Linglong Kong, Bo Liu, Hengshuai Yao

In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL).

Decision Making Distributional Reinforcement Learning +2

Sharpen Focus: Learning with Attention Separability and Consistency

1 code implementation ICCV 2019 Lezi Wang, Ziyan Wu, Srikrishna Karanam, Kuan-Chuan Peng, Rajat Vikram Singh, Bo Liu, Dimitris N. Metaxas

Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks.

General Classification Image Classification

Evolving the pulmonary nodules diagnosis from classical approaches to deep learning aided decision support: three decades development course and future prospect

no code implementations23 Jan 2019 Bo Liu, Wenhao Chi, Xinran Li, Peng Li, Wenhua Liang, Haiping Liu, Wei Wang, Jianxing He

Lung cancer is the commonest cause of cancer deaths worldwide, and its mortality can be reduced significantly by performing early diagnosis and screening.

Robust Matrix Completion State Estimation in Distribution Systems

no code implementations6 Feb 2019 Bo Liu, Hongyu Wu, Yingchen Zhang, Rui Yang, Andrey Bernstein

It can estimate the system state in a low-observability system and has robust estimates without the bad data detection process in the face of multiple bad data.

Matrix Completion

Privacy Preserving Location Data Publishing: A Machine Learning Approach

no code implementations24 Feb 2019 Sina Shaham, Ming Ding, Bo Liu, Shuping Dang, Zihuai Lin, Jun Li

By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use $k$-means algorithm for this purpose.

BIG-bench Machine Learning Clustering +2

HR-TD: A Regularized TD Method to Avoid Over-Generalization

no code implementations ICLR 2019 Ishan Durugkar, Bo Liu, Peter Stone

Temporal Difference learning with function approximation has been widely used recently and has led to several successful results.

Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge

1 code implementation WS 2019 Bo Liu

We present our 7th place solution to the Gendered Pronoun Resolution challenge, which uses BERT without fine-tuning and a novel augmentation strategy designed for contextual embedding token-level tasks.

Optimal Control of Complex Systems through Variational Inference with a Discrete Event Decision Process

no code implementations7 May 2019 Wen Dong, Bo Liu, Fan Yang

However, such real-world complex system control is difficult to achieve because of high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decision maker.

Decision Making Management +1

Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks

no code implementations30 May 2019 Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma, Wei-Shi Zheng

Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential.

Image-to-Image Translation

Non-uniqueness phenomenon of object representation in modelling IT cortex by deep convolutional neural network (DCNN)

no code implementations6 Jun 2019 Qiulei Dong, Bo Liu, Zhanyi Hu

Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modelling approach for neural object representation in primate inferotemporal cortex.

Object

A Joint Planning and Learning Framework for Human-Aided Decision-Making

no code implementations17 Jun 2019 Daoming Lyu, Fangkai Yang, Bo Liu, Steven Gustafson

Conventional reinforcement learning (RL) allows an agent to learn policies via environmental rewards only, with a long and slow learning curve, especially at the beginning stage.

Decision Making General Knowledge +1

Transfer Learning-Based Label Proportions Method with Data of Uncertainty

no code implementations19 Aug 2019 Yanshan Xiao, HuaiPei Wang, Bo Liu

Learning with label proportions (LLP), which is a learning task that only provides unlabeled data in bags and each bag's label proportion, has widespread successful applications in practice.

Transfer Learning

Optimal Function Approximation with Relu Neural Networks

no code implementations9 Sep 2019 Bo Liu, Yi Liang

We consider in this paper the optimal approximations of convex univariate functions with feed-forward Relu neural networks.

A Human-Centered Data-Driven Planner-Actor-Critic Architecture via Logic Programming

no code implementations18 Sep 2019 Daoming Lyu, Fangkai Yang, Bo Liu, Steven Gustafson

Recent successes of Reinforcement Learning (RL) allow an agent to learn policies that surpass human experts but suffers from being time-hungry and data-hungry.

General Knowledge Reinforcement Learning (RL)

DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs

1 code implementation28 Sep 2019 Yunbo Wang, Bo Liu, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei, Joshua B. Tenenbaum

A major difficulty of solving continuous POMDPs is to infer the multi-modal distribution of the unobserved true states and to make the planning algorithm dependent on the perceived uncertainty.

Continuous Control

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

1 code implementation ICML 2020 Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

With the help of the emphasis critic and the canonical value function critic, we show convergence for COF-PAC, where the critics are linear and the actor can be nonlinear.

Vocal Bursts Valence Prediction

FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10

no code implementations18 Nov 2019 Ke He, Bo Liu, Yu Zhang, Andrew Ling, Dian Gu

In this paper, we firstly propose the FeCaffe, i. e. FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e. g. training and inference with Caffe.

Heterogeneous Deep Graph Infomax

1 code implementation19 Nov 2019 Yuxiang Ren, Bo Liu, Chao Huang, Peng Dai, Liefeng Bo, Jiawei Zhang

The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering.

Classification Clustering +4

Object-Guided Instance Segmentation for Biological Images

no code implementations20 Nov 2019 Jingru Yi, Hui Tang, Pengxiang Wu, Bo Liu, Daniel J. Hoeppner, Dimitris N. Metaxas, Lianyi Han, Wei Fan

Along with the instance normalization, the model is able to recover the target object distribution and suppress the distribution of neighboring attached objects.

Clustering Instance Segmentation +6

Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons

1 code implementation21 Nov 2019 Ligong Han, Ruijiang Gao, Mun Kim, Xin Tao, Bo Liu, Dimitris Metaxas

Conditional generative adversarial networks have shown exceptional generation performance over the past few years.

Attribute Generative Adversarial Network

Deep Object Co-segmentation via Spatial-Semantic Network Modulation

1 code implementation29 Nov 2019 Kaihua Zhang, Jin Chen, Bo Liu, Qingshan Liu

With the multi-resolution features of the relevant images as input, we design a spatial modulator to learn a mask for each image.

General Classification Image Classification +2

Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network

1 code implementation2 Jan 2020 Jin Chen, Huihui Song, Kaihua Zhang, Bo Liu, Qingshan Liu

Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP).

Saliency Prediction Video Saliency Detection +1

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

1 code implementation ICML 2020 Shangtong Zhang, Bo Liu, Shimon Whiteson

Namely, the optimization problem in GenDICE is not a convex-concave saddle-point problem once nonlinearity in optimization variable parameterization is introduced to ensure positivity, so any primal-dual algorithm is not guaranteed to converge or find the desired solution.

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 1: Theory

no code implementations12 Feb 2020 Bo Liu

For one-hidden-layer ReLU networks, we prove that all differentiable local minima are global inside differentiable regions.

Some Geometrical and Topological Properties of DNNs' Decision Boundaries

no code implementations7 Mar 2020 Bo Liu, Mengya Shen

Geometry and topology of decision regions are closely related with classification performance and robustness against adversarial attacks.

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection

1 code implementation CVPR 2020 Kaihua Zhang, Tengpeng Li, Shiwen Shen, Bo Liu, Jin Chen, Qingshan Liu

Second, we develop an attention graph clustering algorithm to discriminate the common objects from all the salient foreground objects in an unsupervised fashion.

Clustering Co-Salient Object Detection +1

Dual Temporal Memory Network for Efficient Video Object Segmentation

no code implementations13 Mar 2020 Kaihua Zhang, Long Wang, Dong Liu, Bo Liu, Qingshan Liu, Zhu Li

We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories to address the temporal modeling in VOS.

Object One-shot visual object segmentation +4

Estimation of genome size using k-mer frequencies from corrected long reads

1 code implementation26 Mar 2020 Hengchao Wang, Bo Liu, Yan Zhang, Fan Jiang, Yuwei Ren, Lijuan Yin, Hangwei Liu, Sen Wang, Wei Fan

We show that corrected third-generation data can be used to count k-mer frequencies and estimate genome size reliably, in replacement of using second-generation data.

Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition

1 code implementation CVPR 2020 Chih-Hui Ho, Bo Liu, Tz-Ying Wu, Nuno Vasconcelos

Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task.

Object Object Recognition +2

APPLD: Adaptive Planner Parameter Learning from Demonstration

no code implementations31 Mar 2020 Xuesu Xiao, Bo Liu, Garrett Warnell, Jonathan Fink, Peter Stone

Existing autonomous robot navigation systems allow robots to move from one point to another in a collision-free manner.

Robot Navigation

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

1 code implementation22 Apr 2020 Shangtong Zhang, Bo Liu, Shimon Whiteson

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable.

reinforcement-learning Reinforcement Learning (RL)

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

no code implementations22 May 2020 Jia-Wei Chen, Rongfang Wang, Fan Ding, Bo Liu, Licheng Jiao, Jie Zhang

Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset.

Change Detection

Few-Shot Open-Set Recognition using Meta-Learning

1 code implementation CVPR 2020 Bo Liu, Hao Kang, Haoxiang Li, Gang Hua, Nuno Vasconcelos

It is argued that the classic softmax classifier is a poor solution for open-set recognition, since it tends to overfit on the training classes.

Classification General Classification +3

Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

no code implementations31 May 2020 Feifan Lv, Bo Liu, Feng Lu

This paper proposes a new light-weight convolutional neural network (5k parameters) for non-uniform illumination image enhancement to handle color, exposure, contrast, noise and artifacts, etc., simultaneously and effectively.

Image Enhancement

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

1 code implementation6 Jun 2020 Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms.

reinforcement-learning Reinforcement Learning (RL)

Finite-Sample Analysis of Proximal Gradient TD Algorithms

no code implementations6 Jun 2020 Bo Liu, Ji Liu, Mohammad Ghavamzadeh, Sridhar Mahadevan, Marek Petrik

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms.

Regularized Off-Policy TD-Learning

no code implementations NeurIPS 2012 Bo Liu, Sridhar Mahadevan, Ji Liu

We present a novel $l_1$ regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computational complexity.

feature selection

Stable and Efficient Policy Evaluation

no code implementations6 Jun 2020 Daoming Lyu, Bo Liu, Matthieu Geist, Wen Dong, Saad Biaz, Qi. Wang

Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy.

Reinforcement Learning (RL)

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 2: Experiments and Analysis

no code implementations15 Jun 2020 Bo Liu

The existence of local minima for one-hidden-layer ReLU networks has been investigated theoretically in [8].

RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network

1 code implementation4 Jul 2020 Chuan Ma, Jun Li, Ming Ding, Bo Liu, Kang Wei, Jian Weng, H. Vincent Poor

Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection.

Generative Adversarial Network

Meta-Learning with Network Pruning

no code implementations ECCV 2020 Hongduan Tian, Bo Liu, Xiao-Tong Yuan, Qingshan Liu

To remedy this deficiency, we propose a network pruning based meta-learning approach for overfitting reduction via explicitly controlling the capacity of network.

Few-Shot Learning Network Pruning

Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

1 code implementation17 Aug 2020 Jingru Yi, Pengxiang Wu, Bo Liu, Qiaoying Huang, Hui Qu, Dimitris Metaxas

To address this issue, in this work we extend the horizontal keypoint-based object detector to the oriented object detection task.

Object object-detection +3

Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature

no code implementations29 Aug 2020 Bo Liu, Qiulei Dong, Zhanyi Hu

In addition, considering that the visual features from categorization CNNs are generally inconsistent with their semantic features, a simple feature selection strategy is introduced for extracting more compact semantic visual features.

feature selection Object Recognition +1

Variance-Reduced Off-Policy Memory-Efficient Policy Search

no code implementations14 Sep 2020 Daoming Lyu, Qi Qi, Mohammad Ghavamzadeh, Hengshuai Yao, Tianbao Yang, Bo Liu

To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples.

Reinforcement Learning (RL) Stochastic Optimization

Spin-wave focusing induced skyrmion generation

no code implementations17 Sep 2020 Zhenyu Wang, Z. -X. Li, Ruifang Wang, Bo Liu, Hao Meng, Yunshan Cao, Peng Yan

We propose a new method to generate magnetic skyrmions through spin-wave focusing in chiral ferromagnets. A lens is constructed to focus spin waves by a curved interface between two ferromagnetic thin films with different perpendicular magnetic anisotropies.

Mesoscale and Nanoscale Physics

Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking

1 code implementation21 Sep 2020 Fei Xie, Wankou Yang, Bo Liu, Kaihua Zhang, Wanli Xue, WangMeng Zuo

Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations.

Segmentation Semantic Segmentation +5

Google Landmark Recognition 2020 Competition Third Place Solution

2 code implementations11 Oct 2020 Qishen Ha, Bo Liu, Fuxu Liu, Peiyuan Liao

We present our third place solution to the Google Landmark Recognition 2020 competition.

Landmark Recognition

An Industry Evaluation of Embedding-based Entity Alignment

1 code implementation COLING 2020 Ziheng Zhang, Jiaoyan Chen, Xi Chen, Hualuo Liu, Yuejia Xiang, Bo Liu, Yefeng Zheng

Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage.

Entity Alignment Knowledge Graphs

The SLT 2021 children speech recognition challenge: Open datasets, rules and baselines

no code implementations13 Nov 2020 Fan Yu, Zhuoyuan Yao, Xiong Wang, Keyu An, Lei Xie, Zhijian Ou, Bo Liu, Xiulin Li, Guanqiong Miao

Automatic speech recognition (ASR) has been significantly advanced with the use of deep learning and big data.

Sound Audio and Speech Processing

When Machine Learning Meets Privacy: A Survey and Outlook

no code implementations24 Nov 2020 Bo Liu, Ming Ding, Sina Shaham, Wenny Rahayu, Farhad Farokhi, Zihuai Lin

The newly emerged machine learning (e. g. deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems.

BIG-bench Machine Learning

Towards Playing Full MOBA Games with Deep Reinforcement Learning

no code implementations NeurIPS 2020 Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.

Dota 2 reinforcement-learning +1

D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization

no code implementations3 Dec 2020 Bo Liu, Ranglei Wu, Xiuli Bi, Bin Xiao, Weisheng Li, Guoyin Wang, Xinbo Gao

The unfixed encoder autonomously learns the image fingerprints that differentiate between the tampered and non-tampered regions, whereas the fixed encoder intentionally provides the direction information that assists the learning and detection of the network.

Binary Classification

Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation

no code implementations ICCV 2021 Jingyi Cao, Bo Liu, Yunqian Wen, Rong Xie, Li Song

The popularization of intelligent devices including smartphones and surveillance cameras results in more serious privacy issues.

De-identification

A Coach-Player Framework for Dynamic Team Composition

no code implementations1 Jan 2021 Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Anima Anandkumar

The performance of our method is comparable or even better than the setting where all players have a full view of the environment, but no coach.

Zero-shot Generalization

Discrete Knowledge Graph Embedding based on Discrete Optimization

no code implementations13 Jan 2021 Yunqi Li, Shuyuan Xu, Bo Liu, Zuohui Fu, Shuchang Liu, Xu Chen, Yongfeng Zhang

This paper proposes a discrete knowledge graph (KG) embedding (DKGE) method, which projects KG entities and relations into the Hamming space based on a computationally tractable discrete optimization algorithm, to solve the formidable storage and computation cost challenges in traditional continuous graph embedding methods.

Knowledge Graph Embedding

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

1 code implementation NeurIPS 2020 Lemeng Wu, Bo Liu, Peter Stone, Qiang Liu

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures.

Continual Learning Image Classification +1

Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations

no code implementations25 Feb 2021 Bo Liu

A motivating example is given to explain the reason for the existence of spurious local minima: each output neuron of deep fully-connected networks and CNNs with piecewise linear activations produces a continuous piecewise linear (CPWL) output, and different pieces of CPWL output can fit disjoint groups of data samples when minimizing the empirical risk.

IdentityDP: Differential Private Identification Protection for Face Images

no code implementations2 Mar 2021 Yunqian Wen, Li Song, Bo Liu, Ming Ding, Rong Xie

We propose IdentityDP, a face anonymization framework that combines a data-driven deep neural network with a differential privacy (DP) mechanism.

De-identification Disentanglement +2

DP-Image: Differential Privacy for Image Data in Feature Space

no code implementations12 Mar 2021 Hanyu Xue, Bo Liu, Ming Ding, Tianqing Zhu, Dayong Ye, Li Song, Wanlei Zhou

The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public.

Semi-supervised Long-tailed Recognition using Alternate Sampling

no code implementations1 May 2021 Bo Liu, Haoxiang Li, Hao Kang, Nuno Vasconcelos, Gang Hua

A consistency loss has been introduced to limit the impact from unlabeled data while leveraging them to update the feature embedding.

GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition

no code implementations ICCV 2021 Bo Liu, Haoxiang Li, Hao Kang, Gang Hua, Nuno Vasconcelos

A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes.

Transfer Learning

Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition

no code implementations1 May 2021 Bo Liu, Haoxiang Li, Hao Kang, Gang Hua, Nuno Vasconcelos

It is shown that, unlike class-balanced sampling, this is an adversarial augmentation strategy.

Sparse Pose Trajectory Completion

no code implementations1 May 2021 Bo Liu, Mandar Dixit, Roland Kwitt, Gang Hua, Nuno Vasconcelos

In the absence of dense pose sampling in image space, these latent space trajectories provide cross-modal guidance for learning.

Novel View Synthesis Object

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

1 code implementation18 May 2021 Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Animashree Anandkumar

Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players.

Multi-agent Reinforcement Learning reinforcement-learning +3

Neural Auto-Curricula

1 code implementation4 Jun 2021 Xidong Feng, Oliver Slumbers, Ziyu Wan, Bo Liu, Stephen Mcaleer, Ying Wen, Jun Wang, Yaodong Yang

When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.

Multi-agent Reinforcement Learning

Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training

no code implementations ACL 2021 Li-Ming Zhan, Haowen Liang, Bo Liu, Lu Fan, Xiao-Ming Wu, Albert Y. S. Lam

Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection.

Intent Detection Outlier Detection +1

DeepACG: Co-Saliency Detection via Semantic-Aware Contrast Gromov-Wasserstein Distance

no code implementations CVPR 2021 Kaihua Zhang, Mingliang Dong, Bo Liu, Xiao-Tong Yuan, Qingshan Liu

This dense correlation volumes enables the network to accurately discover the structured pair-wise pixel similarities among the common salient objects.

Saliency Detection

Language-Level Semantics Conditioned 3D Point Cloud Segmentation

no code implementations1 Jul 2021 Bo Liu, Shuang Deng, Qiulei Dong, Zhanyi Hu

In this work, a language-level Semantics Conditioned framework for 3D Point cloud segmentation, called SeCondPoint, is proposed, where language-level semantics are introduced to condition the modeling of point feature distribution as well as the pseudo-feature generation, and a feature-geometry-based mixup approach is further proposed to facilitate the distribution learning.

Point Cloud Segmentation Segmentation +2

Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation

1 code implementation7 Jul 2021 Shuang Deng, Bo Liu, Qiulei Dong, Zhanyi Hu

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis.

3D Point Cloud Classification Point Cloud Classification

Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds

no code implementations8 Jul 2021 Shuang Deng, Qiulei Dong, Bo Liu, Zhanyi Hu

The proposed network is iteratively updated with its predicted pseudo labels, where a superpoint generation module is introduced for extracting superpoints from 3D point clouds, and a pseudo-label optimization module is explored for automatically assigning pseudo labels to the unlabeled points under the constraint of the extracted superpoints.

Point Cloud Segmentation Pseudo Label +2

TDM: Trustworthy Decision-Making via Interpretability Enhancement

no code implementations13 Aug 2021 Daoming Lyu, Fangkai Yang, Hugh Kwon, Wen Dong, Levent Yilmaz, Bo Liu

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy.

Decision Making

OOWL500: Overcoming Dataset Collection Bias in the Wild

no code implementations24 Aug 2021 Brandon Leung, Chih-Hui Ho, Amir Persekian, David Orozco, Yen Chang, Erik Sandstrom, Bo Liu, Nuno Vasconcelos

Second, it is used to show that the augmentation of in the wild datasets, such as ImageNet, with in the lab data, such as OOWL500, can significantly decrease these biases, leading to object recognizers of improved generalization.

Adversarial Attack Data Augmentation +2

DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks

no code implementations1 Oct 2021 Ahmet F. Budak, Prateek Bhansali, Bo Liu, Nan Sun, David Z. Pan, Chandramouli V. Kashyap

The key contributions of this paper are a novel sample-efficient two-stage deep learning optimization framework leveraging RL actor-critic algorithms, and a recipe to extend it on large industrial circuits using critical device identification.

Reinforcement Learning (RL)

Trustworthy AI: From Principles to Practices

no code implementations4 Oct 2021 Bo Li, Peng Qi, Bo Liu, Shuai Di, Jingen Liu, JiQuan Pei, JinFeng Yi, BoWen Zhou

In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems.

Fairness

Google Landmark Retrieval 2021 Competition Third Place Solution

no code implementations9 Oct 2021 Qishen Ha, Bo Liu, Hongwei Zhang

We present our solutions to the Google Landmark Challenges 2021, for both the retrieval and the recognition tracks.

Retrieval

BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning

1 code implementation ICCV 2021 Zhirui Dai, Yuepeng Jiang, Yi Li, Bo Liu, Antoni B. Chan, Nuno Vasconcelos

A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed.

Pose Estimation

Conflict-Averse Gradient Descent for Multi-task Learning

3 code implementations NeurIPS 2021 Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, Qiang Liu

The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks.

Multi-Task Learning

Artificial intelligence enabled radio propagation for communications-Part I: Channel characterization and antenna-channel optimization

no code implementations24 Nov 2021 Chen Huang, Ruisi He, Bo Ai, Andreas F. Molisch, Buon Kiong Lau, Katsuyuki Haneda, Bo Liu, Cheng-Xiang Wang, Mi Yang, Claude Oestges, Zhangdui Zhong

To provide higher data rates, as well as better coverage, cost efficiency, security, adaptability, and scalability, the 5G and beyond 5G networks are developed with various artificial intelligence techniques.

Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling

no code implementations24 Nov 2021 Chen Huang, Ruisi He, Bo Ai, Andreas F. Molisch, Buon Kiong Lau, Katsuyuki Haneda, Bo Liu, Cheng-Xiang Wang, Mi Yang, Claude Oestges, Zhangdui Zhong

This two-part paper investigates the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels.

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings

no code implementations25 Nov 2021 Kingsley Nweye, Bo Liu, Peter Stone, Zoltan Nagy

Building upon prior research that highlighted the need for standardizing environments for building control research, and inspired by recently introduced challenges for real life reinforcement learning control, here we propose a non-exhaustive set of nine real world challenges for reinforcement learning control in grid-interactive buildings.

Model Predictive Control Multi-agent Reinforcement Learning +2

Text Mining Drug/Chemical-Protein Interactions using an Ensemble of BERT and T5 Based Models

no code implementations30 Nov 2021 Virginia Adams, Hoo-chang Shin, Carol Anderson, Bo Liu, Anas Abidin

In Track-1 of the BioCreative VII Challenge participants are asked to identify interactions between drugs/chemicals and proteins.

Relation Relation Extraction +2

Neural Auto-Curricula in Two-Player Zero-Sum Games

1 code implementation NeurIPS 2021 Xidong Feng, Oliver Slumbers, Ziyu Wan, Bo Liu, Stephen Mcaleer, Ying Wen, Jun Wang, Yaodong Yang

When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.

Multi-agent Reinforcement Learning Vocal Bursts Valence Prediction

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning

1 code implementation31 Dec 2021 Xidong Feng, Bo Liu, Jie Ren, Luo Mai, Rui Zhu, Haifeng Zhang, Jun Wang, Yaodong Yang

Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations.

Atari Games Meta Reinforcement Learning +3

A Critical Review of Inductive Logic Programming Techniques for Explainable AI

no code implementations31 Dec 2021 Zheng Zhang, Liangliang Xu, Levent Yilmaz, Bo Liu

Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption.

BIG-bench Machine Learning Explainable artificial intelligence +2

HardBoost: Boosting Zero-Shot Learning with Hard Classes

no code implementations14 Jan 2022 Bo Liu, Lihua Hu, Zhanyi Hu, Qiulei Dong

This work is a systematical analysis on the so-called hard class problem in zero-shot learning (ZSL), that is, some unseen classes disproportionally affect the ZSL performances than others, as well as how to remedy the problem by detecting and exploiting hard classes.

Zero-Shot Learning

STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence

no code implementations24 Jan 2022 Liangliang Xu, Daoming Lyu, Yangchen Pan, Aiwen Jiang, Bo Liu

This paper proposes Short-Term VOlatility-controlled Policy Search (STOPS), a novel algorithm that solves risk-averse problems by learning from short-term trajectories instead of long-term trajectories.

PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent

no code implementations1 Feb 2022 Daoming Lyu, Bo Liu, Jianshu Chen

We consider the problem of multi-task reasoning (MTR), where an agent can solve multiple tasks via (first-order) logic reasoning.

Modeling User Behavior with Graph Convolution for Personalized Product Search

1 code implementation12 Feb 2022 Fan Lu, Qimai Li, Bo Liu, Xiao-Ming Wu, Xiaotong Zhang, Fuyu Lv, Guli Lin, Sen Li, Taiwei Jin, Keping Yang

Our approach can be seamlessly integrated with existing latent space based methods and be potentially applied in any product retrieval method that uses purchase history to model user preferences.

Learning Semantic Representations Retrieval

Learning a Shield from Catastrophic Action Effects: Never Repeat the Same Mistake

no code implementations19 Feb 2022 Shahaf S. Shperberg, Bo Liu, Peter Stone

When humans make catastrophic mistakes, they are expected to learn never to repeat them, such as a toddler who touches a hot stove and immediately learns never to do so again.

Continual Learning Safe Reinforcement Learning

Domain-level Pairwise Semantic Interaction for Aspect-Based Sentiment Classification

no code implementations21 Feb 2022 Zhenxin Wu, Jiazheng Gong, Kecen Guo, Guanye Liang, Qingliang Che, Bo Liu

Aspect-based sentiment classification (ABSC) is a very challenging subtask of sentiment analysis (SA) and suffers badly from the class-imbalance.

Classification Sentence +2

One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy

no code implementations13 Mar 2022 Dayong Ye, Sheng Shen, Tianqing Zhu, Bo Liu, Wanlei Zhou

The experimental results show the method to be an effective and timely defense against both membership inference and model inversion attacks with no reduction in accuracy.

Label-only Model Inversion Attack: The Attack that Requires the Least Information

no code implementations13 Mar 2022 Dayong Ye, Tianqing Zhu, Shuai Zhou, Bo Liu, Wanlei Zhou

In launching a contemporary model inversion attack, the strategies discussed are generally based on either predicted confidence score vectors, i. e., black-box attacks, or the parameters of a target model, i. e., white-box attacks.

Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector

no code implementations17 Mar 2022 Bo Liu, Qiulei Dong, Zhanyi Hu

Firstly, we propose a Semantic-diversity transfer Network (SetNet) addressing the first two limitations, where 1) a multiple-attention architecture and a diversity regularizer are proposed to learn multiple local visual features that are more consistent with semantic attributes and 2) a projector ensemble that geometrically takes diverse local features as inputs is proposed to model visual-semantic relations from diverse local perspectives.

Generalized Zero-Shot Learning Transfer Learning

Continual Learning and Private Unlearning

1 code implementation24 Mar 2022 Bo Liu, Qiang Liu, Peter Stone

As intelligent agents become autonomous over longer periods of time, they may eventually become lifelong counterparts to specific people.

Continual Learning

An Iterative Co-Training Transductive Framework for Zero Shot Learning

no code implementations30 Mar 2022 Bo Liu, Lihua Hu, Qiulei Dong, Zhanyi Hu

How to generate pseudo labels for unseen-class samples and how to use such usually noisy pseudo labels are two critical issues in transductive learning.

Transductive Learning Zero-Shot Learning

Effective Mutation Rate Adaptation through Group Elite Selection

no code implementations11 Apr 2022 Akarsh Kumar, Bo Liu, Risto Miikkulainen, Peter Stone

GESMR co-evolves a population of solutions and a population of MRs, such that each MR is assigned to a group of solutions.

Evolutionary Algorithms Image Classification

Implicit semantic-based personalized micro-videos recommendation

no code implementations6 May 2022 Bo Liu

With the rapid development of mobile Internet and big data, a huge amount of data is generated in the network, but the data that users are really interested in a very small portion.

Retrieval

Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

1 code implementation23 May 2022 Jiazhi Xu, Sheng Huang, Fengtao Zhou, Luwen Huangfu, Daniel Zeng, Bo Liu

Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels.

Knowledge Distillation Multi-Label Image Classification

Video object tracking based on YOLOv7 and DeepSORT

no code implementations25 Jul 2022 Feng Yang, Xingle Zhang, Bo Liu

Among the current popular MOT methods based on deep learning, Detection Based Tracking (DBT) is the most widely used in industry, and the performance of them depend on their object detection network.

Multiple Object Tracking Object +3

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

2 code implementations17 Aug 2022 Bo Liu, Yihao Feng, Qiang Liu, Peter Stone

Furthermore, we introduce the metric residual network (MRN) that deliberately decomposes the action-value function Q(s, a, g) into the negated summation of a metric plus a residual asymmetric component.

reinforcement-learning Reinforcement Learning (RL)

GaitMM: Multi-Granularity Motion Sequence Learning for Gait Recognition

1 code implementation18 Sep 2022 Lei Wang, Bo Liu, Bincheng Wang, Fuqiang Yu

In this study, we propose a multi-granularity motion representation network (GaitMM) for gait sequence learning.

Gait Recognition

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

no code implementations19 Sep 2022 Mao Ye, Bo Liu, Stephen Wright, Peter Stone, Qiang Liu

Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning.

Bilevel Optimization Continual Learning +3

Two-Stream Transformer for Multi-Label Image Classification

1 code implementation ACMMM 2022 Xuelin Zhu, Jiuxin Cao, Jiawei Ge, Weijia Liu, Bo Liu

Specifically, in each layer of TSFormer, a cross-modal attention module is developed to aggregate visual features from spatial stream into semantic stream and update label semantics via a residual connection.

Classification Multi-Label Image Classification +1

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers

no code implementations20 Oct 2022 Guangsheng Zhang, Bo Liu, Huan Tian, Tianqing Zhu, Ming Ding, Wanlei Zhou

As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale.

Attribute

Spatial Temporal Graph Convolution with Graph Structure Self-learning for Early MCI Detection

no code implementations11 Nov 2022 Yunpeng Zhao, Fugen Zhou, Bin Guo, Bo Liu

The proposed spatial temporal graph convolution block directly exploits BOLD time series as input features, which provides an interesting view for rsfMRI-based preclinical AD diagnosis.

Self-Learning Time Series +1

TorchOpt: An Efficient Library for Differentiable Optimization

1 code implementation13 Nov 2022 Jie Ren, Xidong Feng, Bo Liu, Xuehai Pan, Yao Fu, Luo Mai, Yaodong Yang

TorchOpt further provides a high-performance distributed execution runtime.

AlignVE: Visual Entailment Recognition Based on Alignment Relations

no code implementations16 Nov 2022 Biwei Cao, Jiuxin Cao, Jie Gui, Jiayun Shen, Bo Liu, Lei He, Yuan Yan Tang, James Tin-Yau Kwok

Such approaches, however, ignore the VE's unique nature of relation inference between the premise and hypothesis.

Question Answering Relation +2

Intelligent Computing: The Latest Advances, Challenges and Future

no code implementations21 Nov 2022 Shiqiang Zhu, Ting Yu, Tao Xu, Hongyang Chen, Schahram Dustdar, Sylvain Gigan, Deniz Gunduz, Ekram Hossain, Yaochu Jin, Feng Lin, Bo Liu, Zhiguo Wan, Ji Zhang, Zhifeng Zhao, Wentao Zhu, Zuoning Chen, Tariq Durrani, Huaimin Wang, Jiangxing Wu, Tongyi Zhang, Yunhe Pan

In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications.

Complete cavity map of the C. elegans connectome

no code implementations7 Dec 2022 Bo Liu, Rongmei Yang, Hao Wang, Linyuan Lü

This study reports for the first time a complete cavity map of C. elegans neural network, developing a new method for mining higher-order structures that can be applied by researchers in neuroscience, network science and other interdisciplinary fields to explore higher-order structural markers of complex systems.

Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition

no code implementations CVPR 2023 Leming Guo, Wanli Xue, Qing Guo, Bo Liu, Kaihua Zhang, Tiantian Yuan, ShengYong Chen

Existing results in [9, 20, 25, 36] have indicated that, as the frontal component of the overall model, the spatial perception module used for spatial feature extraction tends to be insufficiently trained.

Knowledge Distillation Sign Language Recognition

Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability

no code implementations ICCV 2023 Yunqian Wen, Bo Liu, Jingyi Cao, Rong Xie, Li Song

To address these issues, we propose IDeudemon, which employs a "divide and conquer" strategy to protect identity and preserve utility step by step while maintaining good explainability.

De-identification

DLBD: A Self-Supervised Direct-Learned Binary Descriptor

1 code implementation CVPR 2023 Bin Xiao, Yang Hu, Bo Liu, Xiuli Bi, Weisheng Li, Xinbo Gao

Since their binarization processes are not a component of the network, the learning-based binary descriptor cannot fully utilize the advances of deep learning.

Binarization Image Retrieval +1

Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning

no code implementations ICCV 2023 Tiankang Su, Huihui Song, Dong Liu, Bo Liu, Qingshan Liu

We integrate our offline training and online fine-tuning in a unified framework for unsupervised video object segmentation and dub our method Online Adversarial Self-Tuning (OAST).

Object Pseudo Label +4

Enhance Local Consistency in Federated Learning: A Multi-Step Inertial Momentum Approach

no code implementations11 Feb 2023 Yixing Liu, Yan Sun, Zhengtao Ding, Li Shen, Bo Liu, DaCheng Tao

Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the local partial participation clients, which precipitates the local client-drifts problems and sparks off the unstable and slow convergence, especially on the aggravated heterogeneous dataset.

Edge-computing Federated Learning

MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling

no code implementations10 Mar 2023 Jiaqi Xu, Bo Liu, Yunkuo Chen, Mengli Cheng, Xing Shi

Specifically, we design a Text-Guided MultiWay-Sampler based on adapt-pooling residual mapping and self-attention modules to sample long sequences and fuse multi-modal features, which reduces the computational costs and addresses performance degradation caused by previous samplers.

 Ranked #1 on TGIF-Transition on TGIF-QA (using extra training data)

Multi-Label Classification Multiple-choice +8

Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustness

no code implementations23 Mar 2023 Huajie Chen, Tianqing Zhu, Yuan Zhao, Bo Liu, Xin Yu, Wanlei Zhou

By avoiding high-frequency artifacts and manipulating the frequency distribution of the embedded feature map, LIDS achieves improved robustness against attacks that distort the high-frequency components of container images.

Retrieval Specificity

Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation

1 code implementation25 Mar 2023 Xiaoxiao He, Chaowei Tan, Bo Liu, Liping Si, Weiwu Yao, Liang Zhao, Di Liu, Qilong Zhangli, Qi Chang, Kang Li, Dimitris N. Metaxas

The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost.

Federated Learning Few-Shot Learning +1

Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection

no code implementations28 Mar 2023 Tao He, Sheng Huang, Wenhao Tang, Bo Liu

DKE employs a segmentation module to segment the shrunken text region as the text kernel, then expands the text kernel contour to obtain text boundary by regressing the vertex-wise offsets.

Graph Matching Scene Text Detection +2

No Place to Hide: Dual Deep Interaction Channel Network for Fake News Detection based on Data Augmentation

no code implementations31 Mar 2023 Biwei Cao, Lulu Hua, Jiuxin Cao, Jie Gui, Bo Liu, James Tin-Yau Kwok

Different from popular methods which take full advantage of the propagation topology structure, in this paper, we propose a novel framework for fake news detection from perspectives of semantic, emotion and data enhancement, which excavates the emotional evolution patterns of news participants during the propagation process, and a dual deep interaction channel network of semantic and emotion is designed to obtain a more comprehensive and fine-grained news representation with the consideration of comments.

Data Augmentation Fake News Detection

Practical Lessons on Optimizing Sponsored Products in eCommerce

no code implementations5 Apr 2023 Yanbing Xue, Bo Liu, Weizhi Du, Jayanth Korlimarla, Musen Men

In this paper, we first propose data and feature engineering techniques to handle the aforementioned problems in ad system; after that, we evaluate the benefit of our practical framework on real-world data sets from our traffic logs from online shopping site.

Feature Engineering Multi-Task Learning

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

1 code implementation22 Apr 2023 Bo Liu, Yuqian Jiang, Xiaohan Zhang, Qiang Liu, Shiqi Zhang, Joydeep Biswas, Peter Stone

LLM+P takes in a natural language description of a planning problem, then returns a correct (or optimal) plan for solving that problem in natural language.

Zero-shot Generalization

DPMLBench: Holistic Evaluation of Differentially Private Machine Learning

1 code implementation10 May 2023 Chengkun Wei, Minghu Zhao, Zhikun Zhang, Min Chen, Wenlong Meng, Bo Liu, Yuan Fan, Wenzhi Chen

We also explore some improvements that can maintain model utility and defend against MIAs more effectively.

Image Classification

FAMO: Fast Adaptive Multitask Optimization

1 code implementation NeurIPS 2023 Bo Liu, Yihao Feng, Peter Stone, Qiang Liu

One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL).

Computational Efficiency

Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark

1 code implementation10 Jun 2023 Li Xu, Bo Liu, Ameer Hamza Khan, Lu Fan, Xiao-Ming Wu

With the availability of large-scale, comprehensive, and general-purpose vision-language (VL) datasets such as MSCOCO, vision-language pre-training (VLP) has become an active area of research and proven to be effective for various VL tasks such as visual-question answering.

Medical Report Generation Question Answering +3

An Efficient and Multi-private Key Secure Aggregation for Federated Learning

no code implementations15 Jun 2023 Xue Yang, Zifeng Liu, Xiaohu Tang, Rongxing Lu, Bo Liu

With the emergence of privacy leaks in federated learning, secure aggregation protocols that mainly adopt either homomorphic encryption or threshold secret sharing have been widely developed for federated learning to protect the privacy of the local training data of each client.

Federated Learning

AdaSelection: Accelerating Deep Learning Training through Data Subsampling

no code implementations19 Jun 2023 Minghe Zhang, Chaosheng Dong, Jinmiao Fu, Tianchen Zhou, Jia Liang, Jia Liu, Bo Liu, Michinari Momma, Bryan Wang, Yan Gao, Yi Sun

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.

MRFI: An Open Source Multi-Resolution Fault Injection Framework for Neural Network Processing

1 code implementation20 Jun 2023 Haitong Huang, Cheng Liu, Bo Liu, Xinghua Xue, Huawei Li, Xiaowei Li

It enables users to modify an independent fault configuration file rather than neural network models for the fault injection and vulnerability analysis.

All in One: Multi-task Prompting for Graph Neural Networks

1 code implementation4 Jul 2023 Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan

Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks.

Meta-Learning

Hierarchical Spatio-Temporal Representation Learning for Gait Recognition

no code implementations ICCV 2023 Lei Wang, Bo Liu, Fangfang Liang, Bincheng Wang

While current methods focus on exploiting body part-based representations, they often neglect the hierarchical dependencies between local motion patterns.

Gait Recognition Representation Learning

Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification

1 code implementation ICCV 2023 Wenhao Tang, Sheng Huang, Xiaoxian Zhang, Fengtao Zhou, Yi Zhang, Bo Liu

Moreover, the student is used to update the teacher with an exponential moving average (EMA), which in turn identifies new hard instances for subsequent training iterations and stabilizes the optimization.

Image Classification Multiple Instance Learning

Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce

no code implementations29 Jul 2023 Yibo Wang, Yanbing Xue, Bo Liu, Musen Wen, Wenting Zhao, Stephen Guo, Philip S. Yu

Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems.

Position

Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance

no code implementations16 Aug 2023 Xinghua Xue, Cheng Liu, Bo Liu, Haitong Huang, Ying Wang, Tao Luo, Lei Zhang, Huawei Li, Xiaowei Li

When it is applied on fault-tolerant neural networks enhanced with fault-aware retraining and constrained activation functions, the resulting model accuracy generally shows significant improvement in presence of various faults.

Computational Efficiency

DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction

1 code implementation18 Aug 2023 Xiaoxiao He, Chaowei Tan, Ligong Han, Bo Liu, Leon Axel, Kang Li, Dimitris N. Metaxas

However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed cardiac volumes.

3D Reconstruction

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

no code implementations ICCV 2023 Lei Fan, Bo Liu, Haoxiang Li, Ying Wu, Gang Hua

First, prediction uncertainty should be separately quantified as confusion depicting inter-class uncertainties and ignorance identifying out-of-distribution samples.

Decision Making

Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis

no code implementations18 Sep 2023 Tianyi Song, Jiuxin Cao, Kun Wang, Bo Liu, Xiaofeng Zhang

The current state-of-the-art method combines the features of historical captions, historical frames, and the current captions as conditions for generating the current frame.

Image Generation Story Generation

Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges

no code implementations25 Sep 2023 Tongtong Yuan, Xuange Zhang, Kun Liu, Bo Liu, Chen Chen, Jian Jin, Zhenzhen Jiao

Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance video-and-language understanding.

Anomaly Detection Dense Video Captioning +1

Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts

no code implementations9 Oct 2023 Lizhang Chen, Bo Liu, Kaizhao Liang, Qiang Liu

As we can expect from the results of a random search program, Lion incorporates elements from several existing algorithms, including signed momentum, decoupled weight decay, Polak, and Nesterov momentum, but does not fit into any existing category of theoretically grounded optimizers.

RT-SRTS: Angle-Agnostic Real-Time Simultaneous 3D Reconstruction and Tumor Segmentation from Single X-Ray Projection

1 code implementation12 Oct 2023 Miao Zhu, Qiming Fu, Bo Liu, Mengxi Zhang, Bojian Li, Xiaoyan Luo, Fugen Zhou

In this study, we propose a novel imaging method RT-SRTS which integrates 3D imaging and tumor segmentation into one network based on the multi-task learning (MTL) and achieves real-time simultaneous 3D reconstruction and tumor segmentation from single X-ray projection at any angle.

3D Reconstruction Multi-Task Learning +2

EasyGen: Easing Multimodal Generation with a Bidirectional Conditional Diffusion Model and LLMs

1 code implementation13 Oct 2023 Xiangyu Zhao, Bo Liu, Qijiong Liu, Guangyuan Shi, Xiao-Ming Wu

We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs).

multimodal generation Text Generation +1

Towards Open-World Co-Salient Object Detection with Generative Uncertainty-aware Group Selective Exchange-Masking

1 code implementation16 Oct 2023 Yang Wu, Shenglong Hu, Huihui Song, Kaihua Zhang, Bo Liu, Dong Liu

To simultaneously consider the uncertainty introduced by irrelevant images and the consensus features of the remaining relevant images in the group, we designed a latent variable generator branch and CoSOD transformer branch.

Co-Salient Object Detection object-detection +1

Leveraging Large Language Models for Enhanced Product Descriptions in eCommerce

no code implementations24 Oct 2023 Jianghong Zhou, Bo Liu, Jhalak Nilesh Acharya Yao Hong, Kuang-Chih Lee, Musen Wen

In the dynamic field of eCommerce, the quality and comprehensiveness of product descriptions are pivotal for enhancing search visibility and customer engagement.

Language Modelling

Grasp Multiple Objects with One Hand

1 code implementation24 Oct 2023 Yuyang Li, Bo Liu, Yiran Geng, Puhao Li, Yaodong Yang, Yixin Zhu, Tengyu Liu, Siyuan Huang

The intricate kinematics of the human hand enable simultaneous grasping and manipulation of multiple objects, essential for tasks such as object transfer and in-hand manipulation.

Object

Detecting Generated Images by Real Images Only

no code implementations2 Nov 2023 Xiuli Bi, Bo Liu, Fan Yang, Bin Xiao, Weisheng Li, Gao Huang, Pamela C. Cosman

This paper approaches the generated image detection problem from a new perspective: Start from real images.

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers through Membership Inference Attacks

no code implementations7 Nov 2023 Huan Tian, Guangsheng Zhang, Bo Liu, Tianqing Zhu, Ming Ding, Wanlei Zhou

It leverages the difference in the predictions from both the original and fairness-enhanced models and exploits the observed prediction gaps as attack clues.

Fairness

HiH: A Multi-modal Hierarchy in Hierarchy Network for Unconstrained Gait Recognition

no code implementations19 Nov 2023 Lei Wang, Yinchi Ma, Peng Luan, Wei Yao, CongCong Li, Bo Liu

Gait recognition has achieved promising advances in controlled settings, yet it significantly struggles in unconstrained environments due to challenges such as view changes, occlusions, and varying walking speeds.

Gait Recognition

Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking

no code implementations28 Nov 2023 Jiawei Ge, Xiangmei Chen, Jiuxin Cao, Xuelin Zhu, Bo Liu

However, current VL trackers have not fully exploited the power of VL learning, as they suffer from limitations such as heavily relying on off-the-shelf backbones for feature extraction, ineffective VL fusion designs, and the absence of VL-related loss functions.

Object Tracking Representation Learning

UGG: Unified Generative Grasping

1 code implementation28 Nov 2023 Jiaxin Lu, Hao Kang, Haoxiang Li, Bo Liu, Yiding Yang, QiXing Huang, Gang Hua

Generation-based methods that generate grasping postures conditioned on the object can often produce diverse grasping, but they are insufficient for high grasping success due to lack of discriminative information.

Grasp Generation Object

From Past to Future: Rethinking Eligibility Traces

no code implementations20 Dec 2023 Dhawal Gupta, Scott M. Jordan, Shreyas Chaudhari, Bo Liu, Philip S. Thomas, Bruno Castro da Silva

In this paper, we introduce a fresh perspective on the challenges of credit assignment and policy evaluation.

Integration and Performance Analysis of Artificial Intelligence and Computer Vision Based on Deep Learning Algorithms

no code implementations20 Dec 2023 Bo Liu, Liqiang Yu, Chang Che, Qunwei Lin, Hao Hu, Xinyu Zhao

This paper focuses on the analysis of the application effectiveness of the integration of deep learning and computer vision technologies.

Image Classification object-detection +1

Cross-Layer Optimization for Fault-Tolerant Deep Learning

no code implementations21 Dec 2023 Qing Zhang, Cheng Liu, Bo Liu, Haitong Huang, Ying Wang, Huawei Li, Xiaowei Li

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics.

Bayesian Optimization Quantization

Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification

no code implementations2 Jan 2024 Xuelin Zhu, Jian Liu, Dongqi Tang, Jiawei Ge, Weijia Liu, Bo Liu, Jiuxin Cao

Identifying labels that did not appear during training, known as multi-label zero-shot learning, is a non-trivial task in computer vision.

Knowledge Distillation Multi-Label Classification +1

t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making

1 code implementation4 Jan 2024 William Yue, Bo Liu, Peter Stone

Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks.

Continual Learning Decision Making

Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method

no code implementations6 Jan 2024 Liqiang Yu, Bo Liu, Qunwei Lin, Xinyu Zhao, Chang Che

In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research.

Semantic Similarity Semantic Textual Similarity

Enhancing Essay Scoring with Adversarial Weights Perturbation and Metric-specific AttentionPooling

no code implementations6 Jan 2024 Jiaxin Huang, Xinyu Zhao, Chang Che, Qunwei Lin, Bo Liu

To address the specific needs of ELLs, we propose the use of DeBERTa, a state-of-the-art neural language model, for improving automated feedback tools.

Automated Essay Scoring Language Modelling +2

Cannot find the paper you are looking for? You can Submit a new open access paper.