Search Results for author: Li Zhang

Found 159 papers, 61 papers with code

Multi-Level Gazetteer-Free Geocoding

no code implementations ACL (splurobonlp) 2021 Sayali Kulkarni, Shailee Jain, Mohammad Javad Hosseini, Jason Baldridge, Eugene Ie, Li Zhang

We present a multi-level geocoding model (MLG) that learns to associate texts to geographic coordinates.

SmartCiteCon: Implicit Citation Context Extraction from Academic Literature Using Supervised Learning

no code implementations WOSP 2020 Chenrui Guo, Haoran Cui, Li Zhang, Jiamin Wang, Wei Lu, Jian Wu

The tool is built on a Support Vector Machine (SVM) model trained on a set of 7, 058 manually annotated citation context sentences, curated from 34, 000 papers from the ACL Anthology.

Tracking and Long-Term Identification Using Non-Visual Markers

1 code implementation13 Dec 2021 Michael P. J. Camilleri, Li Zhang, Rasneer S. Bains, Andrew Zisserman, Christopher K. I. Williams

Our objective is to track and identify mice in a cluttered home-cage environment, as a precursor to automated behaviour recognition for biological research.

Visual Tracking

SGM3D: Stereo Guided Monocular 3D Object Detection

1 code implementation3 Dec 2021 Zheyuan Zhou, Liang Du, Xiaoqing Ye, Zhikang Zou, Xiao Tan, Errui Ding, Li Zhang, xiangyang xue, Jianfeng Feng

We innovatively investigate a multi-granularity domain adaptation module (MG-DA) to exploit the network's ability so as to generate stereo-mimic features only based on the monocular cues.

Autonomous Driving Domain Adaptation +1

ALX: Large Scale Matrix Factorization on TPUs

no code implementations3 Dec 2021 Harsh Mehta, Steffen Rendle, Walid Krichene, Li Zhang

We present ALX, an open-source library for distributed matrix factorization using Alternating Least Squares, written in JAX.

Link Prediction

Learning from Mistakes -- A Framework for Neural Architecture Search

no code implementations11 Nov 2021 Bhanu Garg, Li Zhang, Pradyumna Sridhara, Ramtin Hosseini, Eric Xing, Pengtao Xie

We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision.

Neural Architecture Search

iALS++: Speeding up Matrix Factorization with Subspace Optimization

1 code implementation26 Oct 2021 Steffen Rendle, Walid Krichene, Li Zhang, Yehuda Koren

However, iALS does not scale well with large embedding dimensions, d, due to its cubic runtime dependency on d. Coordinate descent variations, iCD, have been proposed to lower the complexity to quadratic in d. In this work, we show that iCD approaches are not well suited for modern processors and can be an order of magnitude slower than a careful iALS implementation for small to mid scale embedding sizes (d ~ 100) and only perform better than iALS on large embeddings d ~ 1000.

Revisiting the Performance of iALS on Item Recommendation Benchmarks

1 code implementation26 Oct 2021 Steffen Rendle, Walid Krichene, Li Zhang, Yehuda Koren

Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications.

Collaborative Filtering Recommendation Systems

SOFT: Softmax-free Transformer with Linear Complexity

no code implementations NeurIPS 2021 Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, Li Zhang

Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

Text-Based Person Search with Limited Data

1 code implementation20 Oct 2021 Xiao Han, Sen He, Li Zhang, Tao Xiang

Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch.

 Ranked #1 on Text based Person Retrieval on CUHK-PEDES (using extra training data)

Contrastive Learning Cross-Modal Retrieval +3

Multi-Frequency Wireless Channel Measurements and Characteristics Analysis in Indoor Corridor Scenarios

no code implementations14 Aug 2021 ZiHao Zhou, Li Zhang, Xinyue Chen, Cheng-Xiang Wang, Jie Huang

In this paper, we conduct wireless channel measurements in indoor corridor scenarios at 2. 4, 5 and 6 GHz bands with bandwidth of 320 MHz.

Progressive Coordinate Transforms for Monocular 3D Object Detection

1 code implementation NeurIPS 2021 Li Wang, Li Zhang, Yi Zhu, Zhi Zhang, Tong He, Mu Li, xiangyang xue

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.

Monocular 3D Object Detection Object Localization

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer

1 code implementation ICCV 2021 Zhihe Lu, Sen He, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels).

Few-Shot Semantic Segmentation Meta-Learning +1

A Unified Efficient Pyramid Transformer for Semantic Segmentation

no code implementations29 Jul 2021 Fangrui Zhu, Yi Zhu, Li Zhang, Chongruo wu, Yanwei Fu, Mu Li

Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries.

Semantic Segmentation

Goal-Oriented Script Construction

1 code implementation INLG (ACL) 2021 Qing Lyu, Li Zhang, Chris Callison-Burch

The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems.

Language Modelling Natural Language Understanding

Global Aggregation then Local Distribution for Scene Parsing

1 code implementation28 Jul 2021 Xiangtai Li, Li Zhang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Xiatian Zhu, Tao Xiang

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation.

Scene Parsing Semantic Segmentation

Oneshot Differentially Private Top-k Selection

no code implementations18 May 2021 Gang Qiao, Weijie J. Su, Li Zhang

Being able to efficiently and accurately select the top-$k$ elements with differential privacy is an integral component of various private data analysis tasks.

Composite Localization for Human Pose Estimation

no code implementations15 May 2021 ZiFan Chen, Xin Qin, Chao Yang, Li Zhang

This work proposes a novel deep learning framework for human pose estimation called composite localization to divide the complex learning objective into two simpler ones: a sparse heatmap to find the keypoint's approximate location and two short-distance offsetmaps to obtain its final precise coordinates.

Pose Estimation

BasisNet: Two-stage Model Synthesis for Efficient Inference

no code implementations7 May 2021 Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka

With early termination, the average cost can be further reduced to 198M MAdds while maintaining accuracy of 80. 0% on ImageNet.

Prediction of clinical tremor severity using Rank Consistent Ordinal Regression

no code implementations3 May 2021 Li Zhang, Vijay Yadav, Vidya Koesmahargyo, Anzar Abbas, Isaac Galatzer-Levy

The videos are coupled with clinician assessed TETRAS scores, which are used as ground truth labels to train the DNN.

Transfer Learning

Delving into Data: Effectively Substitute Training for Black-box Attack

no code implementations CVPR 2021 Wenxuan Wang, Bangjie Yin, Taiping Yao, Li Zhang, Yanwei Fu, Shouhong Ding, Jilin Li, Feiyue Huang, xiangyang xue

Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models.

Adversarial Attack

Optimize Neural Fictitious Self-Play in Regret Minimization Thinking

no code implementations22 Apr 2021 Yuxuan Chen, Li Zhang, Shijian Li, Gang Pan

Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e. g. StarCraft and poker.


Improving Weakly-supervised Object Localization via Causal Intervention

1 code implementation21 Apr 2021 Feifei Shao, Yawei Luo, Li Zhang, Lu Ye, Siliang Tang, Yi Yang, Jun Xiao

The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels.

Weakly-Supervised Object Localization

Visual Goal-Step Inference using wikiHow

1 code implementation EMNLP 2021 Yue Yang, Artemis Panagopoulou, Qing Lyu, Li Zhang, Mark Yatskar, Chris Callison-Burch

Understanding what sequence of steps are needed to complete a goal can help artificial intelligence systems reason about human activities.


Hierarchical Road Topology Learning for Urban Map-less Driving

no code implementations31 Mar 2021 Li Zhang, Faezeh Tafazzoli, Gunther Krehl, Runsheng Xu, Timo Rehfeld, Manuel Schier, Arunava Seal

The majority of current approaches in autonomous driving rely on High-Definition (HD) maps which detail the road geometry and surrounding area.

Autonomous Driving

Learning Dynamic Alignment via Meta-filter for Few-shot Learning

1 code implementation CVPR 2021 Chengming Xu, Chen Liu, Li Zhang, Chengjie Wang, Jilin Li, Feiyue Huang, xiangyang xue, Yanwei Fu

Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.

Few-Shot Learning

Robust and Accurate Object Detection via Adversarial Learning

1 code implementation CVPR 2021 Xiangning Chen, Cihang Xie, Mingxing Tan, Li Zhang, Cho-Jui Hsieh, Boqing Gong

Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection.

AutoML Data Augmentation +1

MoViNets: Mobile Video Networks for Efficient Video Recognition

2 code implementations CVPR 2021 Dan Kondratyuk, Liangzhe Yuan, Yandong Li, Li Zhang, Mingxing Tan, Matthew Brown, Boqing Gong

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference.

Action Classification Action Recognition +2

Automatically detecting the conflicts between software requirements based on finer semantic analysis

1 code implementation3 Mar 2021 Weize Guo, Li Zhang, Xiaoli Lian

Besides, our approach is capable of transforming the natural language functional requirements into eight semantic tuples, which is useful not only the detection of the conflicts between requirements but also some other tasks such as constructing the association between requirements and so on.

EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition

no code implementations7 Feb 2021 Zhen Liang, Rushuang Zhou, Li Zhang, Linling Li, Gan Huang, Zhiguo Zhang, Shin Ishii

The performance of the extracted deep and low-dimensional features by EEGFuseNet is carefully evaluated in an unsupervised emotion recognition application based on three public emotion databases.

EEG Emotion Recognition

Failure Prediction in Production Line Based on Federated Learning: An Empirical Study

no code implementations25 Jan 2021 Ning Ge, Guanghao Li, Li Zhang, Yi Liu Yi Liu

Data protection across organizations is limiting the application of centralized learning (CL) techniques.

Federated Learning

Few-shot Action Recognition with Prototype-centered Attentive Learning

1 code implementation20 Jan 2021 Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua, Li Zhang, Brais Martinez, Tao Xiang

Extensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (10+\%) on the most challenging fine-grained action recognition benchmark.

Contrastive Learning Fine-grained Action Recognition +1

TEAC: Intergrating Trust Region and Max Entropy Actor Critic for Continuous Control

1 code implementation1 Jan 2021 Hongyu Zang, Xin Li, Li Zhang, Peiyao Zhao, Mingzhong Wang

Trust region methods and maximum entropy methods are two state-of-the-art branches used in reinforcement learning (RL) for the benefits of stability and exploration in continuous environments, respectively.

Continuous Control

Hop-Hop Relation-aware Graph Neural Networks

no code implementations21 Dec 2020 Li Zhang, Yan Ge, Haiping Lu

Graph Neural Networks (GNNs) are widely used in graph representation learning.

Knowledge Graph Embedding

Unifying Homophily and Heterophily Network Transformation via Motifs

no code implementations21 Dec 2020 Yan Ge, Jun Ma, Li Zhang, Haiping Lu

Because H2NT can sparsify networks with motif structures, it can also improve the computational efficiency of existing network embedding methods when integrated.

Network Embedding Node Classification

A Systematic Literature Review on Federated Learning: From A Model Quality Perspective

no code implementations1 Dec 2020 Yi Liu, Li Zhang, Ning Ge, Guanghao Li

In this process, the server uses an incentive mechanism to encourage clients to contribute high-quality and large-volume data to improve the global model.

Federated Learning

Direct Classification of Emotional Intensity

no code implementations15 Nov 2020 Jacob Ouyang, Isaac R Galatzer-Levy, Vidya Koesmahargyo, Li Zhang

In this paper, we present a model that can directly predict emotion intensity score from video inputs, instead of deriving from action units.

General Classification

Skin disease diagnosis with deep learning: a review

no code implementations11 Nov 2020 Hongfeng Li, Yini Pan, Jie Zhao, Li Zhang

As an important part of this article, we then review the literature involving deep learning methods for skin disease diagnosis from several aspects according to the specific tasks.

Towards Efficient Scene Understanding via Squeeze Reasoning

1 code implementation6 Nov 2020 Xiangtai Li, Xia Li, Ansheng You, Li Zhang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Zhouchen Lin

Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced.

Instance Segmentation Object Detection +2

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

1 code implementation20 Oct 2020 Yuqian Fu, Li Zhang, Junke Wang, Yanwei Fu, Yu-Gang Jiang

Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs.

Action Recognition Meta-Learning +1

Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed

1 code implementation14 Oct 2020 Dong Li, Sitong Chen, Xudong Liu, YunDa Sun, Li Zhang

In this paper, we propose a balanced filter pruning method for both performance and pruning speed.

Holistic Grid Fusion Based Stop Line Estimation

no code implementations18 Sep 2020 Runsheng Xu, Faezeh Tafazzoli, Li Zhang, Timo Rehfeld, Gunther Krehl, Arunava Seal

Intersection scenarios provide the most complex traffic situations in Autonomous Driving and Driving Assistance Systems.

Autonomous Driving

Reasoning about Goals, Steps, and Temporal Ordering with WikiHow

1 code implementation EMNLP 2020 Li Zhang, Qing Lyu, Chris Callison-Burch

We propose a suite of reasoning tasks on two types of relations between procedural events: goal-step relations ("learn poses" is a step in the larger goal of "doing yoga") and step-step temporal relations ("buy a yoga mat" typically precedes "learn poses").

Cloze Test

Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior

no code implementations8 Sep 2020 Yan Zhang, Zhao Zhang, Yang Wang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.

Graph Learning Representation Learning

Spatial Language Representation with Multi-Level Geocoding

no code implementations21 Aug 2020 Sayali Kulkarni, Shailee Jain, Mohammad Javad Hosseini, Jason Baldridge, Eugene Ie, Li Zhang

We present a multi-level geocoding model (MLG) that learns to associate texts to geographic locations.

Hybrid Template Canonical Correlation Analysis Method for Enhancing SSVEP Recognition under data-limited Condition

no code implementations7 Aug 2020 Runfeng Miao, Li Zhang, Qiang Sun

In this study, an advanced CCA-based algorithn called hybrid template canonical correlation analysis (HTCCA) was proposed to improve the performance of brain-computer interface (BCI) based on steady state visual evoked potential (SSVEP) uuder data-linited condition.

EEG Transfer Learning

Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval

no code implementations7 Aug 2020 Tao Wu, Ellie Ka-In Chio, Heng-Tze Cheng, Yu Du, Steffen Rendle, Dima Kuzmin, Ritesh Agarwal, Li Zhang, John Anderson, Sarvjeet Singh, Tushar Chandra, Ed H. Chi, Wen Li, Ankit Kumar, Xiang Ma, Alex Soares, Nitin Jindal, Pei Cao

In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation.

Information Retrieval Recommendation Systems +1

Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective

no code implementations31 Jul 2020 Yinghuan Shi, Wanqi Yang, Kim-Han Thung, Hao Wang, Yang Gao, Yang Pan, Li Zhang, Dinggang Shen

Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.

A Survey on Concept Factorization: From Shallow to Deep Representation Learning

no code implementations31 Jul 2020 Zhao Zhang, Yan Zhang, Mingliang Xu, Li Zhang, Yi Yang, Shuicheng Yan

In this paper, we therefore survey the recent advances on CF methodologies and the potential benchmarks by categorizing and summarizing the current methods.

Representation Learning

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

2 code implementations ECCV 2020 Xiangtai Li, Xia Li, Li Zhang, Guangliang Cheng, Jianping Shi, Zhouchen Lin, Shaohua Tan, Yunhai Tong

Our insight is that appealing performance of semantic segmentation requires \textit{explicitly} modeling the object \textit{body} and \textit{edge}, which correspond to the high and low frequency of the image.

Semantic Segmentation

A novel deep learning-based method for monochromatic image synthesis from spectral CT using photon-counting detectors

no code implementations20 Jul 2020 Ao Zheng, Hongkai Yang, Li Zhang, Yuxiang Xing

To solve this problem, in this paper, we proposed a novel deep learning-based monochromatic image synthesis method working in sinogram domain.

Image Generation

XingGAN for Person Image Generation

2 code implementations ECCV 2020 Hao Tang, Song Bai, Li Zhang, Philip H. S. Torr, Nicu Sebe

We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i. e., translating the pose of a given person to a desired one.

 Ranked #1 on Pose Transfer on Market-1501 (IS metric)

Pose Transfer

How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning

1 code implementation15 Jul 2020 Yikai Wang, Li Zhang, Yuan YAO, Yanwei Fu

We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.

Data Augmentation Few-Shot Learning

Egocentric Action Recognition by Video Attention and Temporal Context

no code implementations3 Jul 2020 Juan-Manuel Perez-Rua, Antoine Toisoul, Brais Martinez, Victor Escorcia, Li Zhang, Xiatian Zhu, Tao Xiang

In this challenge, action recognition is posed as the problem of simultaneously predicting a single `verb' and `noun' class label given an input trimmed video clip.

Action Recognition

PriceAggregator: An Intelligent System for Hotel Price Fetching

no code implementations30 Jun 2020 Jiangwei Zhang, Li Zhang, Vigneshwaran Raveendran, Ziv Ben-Zuk, Leonard Lu

The major challenge is that each supplier only allows Agoda to fetch for the hotel price with a limited amount of Queries Per Second (QPS).

Self-supervised Video Object Segmentation

no code implementations22 Jun 2020 Fangrui Zhu, Li Zhang, Yanwei Fu, Guodong Guo, Weidi Xie

The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a. k. a.

One-shot visual object segmentation Representation Learning +2

Long-Term Cloth-Changing Person Re-identification

no code implementations26 May 2020 Xuelin Qian, Wenxuan Wang, Li Zhang, Fangrui Zhu, Yanwei Fu, Tao Xiang, Yu-Gang Jiang, xiangyang xue

Specifically, we consider that under cloth-changes, soft-biometrics such as body shape would be more reliable.

Person Re-Identification

SentPWNet: A Unified Sentence Pair Weighting Network for Task-specific Sentence Embedding

no code implementations22 May 2020 Li Zhang, Han Wang, Lingxiao Li

Our model, SentPWNet, exploits the neighboring spatial distribution of each sentence as locality weight to indicate the informative level of sentence pair.

Metric Learning Sentence Embedding

A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis

no code implementations10 May 2020 Li Zhang, Mingliang Wang, Mingxia Liu, Daoqiang Zhang

Deep learning has been recently used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders.

In-Vehicle Object Detection in the Wild for Driverless Vehicles

no code implementations27 Apr 2020 Ranjith Dinakaran, Li Zhang, Richard Jiang

In-vehicle human object identification plays an important role in vision-based automated vehicle driving systems while objects such as pedestrians and vehicles on roads or streets are the primary targets to protect from driverless vehicles.

Object Detection

Direct Speech-to-image Translation

1 code implementation7 Apr 2020 Jiguo Li, Xinfeng Zhang, Chuanmin Jia, Jizheng Xu, Li Zhang, Yue Wang, Siwei Ma, Wen Gao

In this paper, we attempt to translate the speech signals into the image signals without the transcription stage.

Multimedia Sound Audio and Speech Processing

Universal Adversarial Perturbations Generative Network for Speaker Recognition

1 code implementation7 Apr 2020 Jiguo Li, Xinfeng Zhang, Chuanmin Jia, Jizheng Xu, Li Zhang, Yue Wang, Siwei Ma, Wen Gao

Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the adversarial examples, which have been intentionally perturbed to remain almost imperceptible for human.

Speaker Recognition

Learning to fool the speaker recognition

1 code implementation7 Apr 2020 Jiguo Li, Xinfeng Zhang, Jizheng Xu, Li Zhang, Yue Wang, Siwei Ma, Wen Gao

Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention.

Audio and Speech Processing Cryptography and Security Sound

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

2 code implementations CVPR 2020 Qibin Hou, Li Zhang, Ming-Ming Cheng, Jiashi Feng

Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.

Scene Parsing Semantic Segmentation

Instance Credibility Inference for Few-Shot Learning

1 code implementation CVPR 2020 Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu

To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree.

Data Augmentation Few-Shot Image Classification

What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective

1 code implementation CVPR 2020 Qilong Wang, Li Zhang, Banggu Wu, Dongwei Ren, Peihua Li, WangMeng Zuo, QinGhua Hu

Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.

Instance Segmentation Object Detection +1

Feedback Graph Convolutional Network for Skeleton-based Action Recognition

no code implementations17 Mar 2020 Hao Yang, Dan Yan, Li Zhang, Dong Li, YunDa Sun, ShaoDi You, Stephen J. Maybank

It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions.

Action Recognition Graph Convolutional Network +1

Superbloom: Bloom filter meets Transformer

no code implementations11 Feb 2020 John Anderson, Qingqing Huang, Walid Krichene, Steffen Rendle, Li Zhang

We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids.

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

no code implementations4 Feb 2020 Hefei Ling, Yangyang Qin, Li Zhang, Yuxuan Shi, Ping Li

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors.

Automatic marker-free registration of tree point-cloud data based on rotating projection

no code implementations30 Jan 2020 Xiuxian Xu, Pei Wang, Xiaozheng Gan, Ya-Xin Li, Li Zhang, Qing Zhang, Mei Zhou, Yinghui Zhao, Xinwei Li

In coarse registration, point clouds produced by each scan are projected onto a spherical surface to generate a series of two-dimensional (2D) images, which are used to estimate the initial positions of multiple scans.

Semantic Discord: Finding Unusual Local Patterns for Time Series

1 code implementation30 Jan 2020 Li Zhang, Yifeng Gao, Jessica Lin

Finding anomalous subsequence in a long time series is a very important but difficult problem.

Time Series

Searching for Quasi-Periodic Modulations in $γ$-ray Active Galactic Nuclei

no code implementations29 Jan 2020 Pengfei Zhang, Dahai Yan, Jianeng Zhou, Jiancheng Wang, Li Zhang

We perform a systematic search of quasi-periodic variabilities in $\gamma$-ray active galactic nuclei (AGNs) in the third \emph{Fermi} Large Area Telescope source catalog (3FGL).

High Energy Astrophysical Phenomena

Few-shot Action Recognition with Permutation-invariant Attention

no code implementations ECCV 2020 Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip H. S. Torr, Piotr Koniusz

Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class.

Action Recognition Few-Shot Learning +1

Deep Self-representative Concept Factorization Network for Representation Learning

no code implementations13 Dec 2019 Yan Zhang, Zhao Zhang, Zheng Zhang, Mingbo Zhao, Li Zhang, Zheng-Jun Zha, Meng Wang

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features.

Representation Learning

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning

no code implementations20 Nov 2019 Yulin Sun, Zhao Zhang, Weiming Jiang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning.

Representation Learning

PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation

1 code implementation4 Nov 2019 Jie Zhao, Lei Dai, Mo Zhang, Fei Yu, Meng Li, Hongfeng Li, Wenjia Wang, Li Zhang

The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.

Depth creates no more spurious local minima in linear networks

no code implementations25 Sep 2019 Li Zhang

We show that for any convex differentiable loss, a deep linear network has no spurious local minima as long as it is true for the two layer case.

Global Aggregation then Local Distribution in Fully Convolutional Networks

2 code implementations16 Sep 2019 Xiangtai Li, Li Zhang, Ansheng You, Maoke Yang, Kuiyuan Yang, Yunhai Tong

GALD is end-to-end trainable and can be easily plugged into existing FCNs with various global aggregation modules for a wide range of vision tasks, and consistently improves the performance of state-of-the-art object detection and instance segmentation approaches.

Instance Segmentation Object Detection +2

Rényi Differential Privacy of the Sampled Gaussian Mechanism

2 code implementations28 Aug 2019 Ilya Mironov, Kunal Talwar, Li Zhang

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications.

Dynamic Graph Message Passing Networks

no code implementations CVPR 2020 Li Zhang, Dan Xu, Anurag Arnab, Philip H. S. Torr

A fully-connected graph is beneficial for such modelling, however, its computational overhead is prohibitive.

Object Detection Scene Understanding +1

MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks

2 code implementations26 Jul 2019 Zhulin Zhang, Dong Li, Jinhua Wu, YunDa Sun, Li Zhang

Second, all baggage images are captured by specially-designed multi-view camera system to handle pose variation and occlusion, in order to obtain the 3D information of baggage surface as complete as possible.

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

no code implementations26 Jul 2019 Fei Yu, Jie Zhao, Yanjun Gong, Zhi Wang, Yuxi Li, Fan Yang, Bin Dong, Quanzheng Li, Li Zhang

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.

Transfer Learning

Multi-level Domain Adaptive learning for Cross-Domain Detection

no code implementations26 Jul 2019 Rongchang Xie, Fei Yu, Jiachao Wang, Yizhou Wang, Li Zhang

In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment.

Object Detection

Efficient Semantic Scene Completion Network with Spatial Group Convolution

1 code implementation ECCV 2018 Jiahui Zhang, Hao Zhao, Anbang Yao, Yurong Chen, Li Zhang, Hongen Liao

We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.

ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning

no code implementations7 Jul 2019 Mo Zhang, Jie Zhao, Xiang Li, Li Zhang, Quanzheng Li

Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale.

Semantic Segmentation

End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching

no code implementations25 Jun 2019 Li Zhang, Quanhong Wang, Haihua Lu, Yong Zhao

To tackle this problem, we propose a network for disparity estimation based on abundant contextual details and semantic information, called Multi-scale Features Network (MSFNet).

Disparity Estimation Stereo Matching +1

A Closed-form Solution to Universal Style Transfer

2 code implementations ICCV 2019 Ming Lu, Hao Zhao, Anbang Yao, Yurong Chen, Feng Xu, Li Zhang

Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.

Style Transfer

Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks

no code implementations29 May 2019 Ranjith Dinakaran, Philip Easom, Li Zhang, Ahmed Bouridane, Richard Jiang, Eran Edirisinghe

In our work, GAN has been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities.

Object Detection Pedestrian Detection

Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier

no code implementations27 May 2019 Zhao Zhang, Weiming Jiang, Jie Qin, Li Zhang, Fanzhang Li, Min Zhang, Shuicheng Yan

Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers.

Dictionary Learning General Classification

On the Difficulty of Evaluating Baselines: A Study on Recommender Systems

2 code implementations4 May 2019 Steffen Rendle, Li Zhang, Yehuda Koren

Numerical evaluations with comparisons to baselines play a central role when judging research in recommender systems.

Collaborative Filtering Recommendation Systems

Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks

2 code implementations19 Apr 2019 Wenjia Wang, Junxuan Chen, Jie Zhao, Ying Chi, Xuansong Xie, Li Zhang, Xian-Sheng Hua

The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.

Hierarchical method for cataract grading based on retinal images using improved Haar wavelet

no code implementations2 Apr 2019 Lvchen Cao, Huiqi Li, Yanjun Zhang, Liang Xu, Li Zhang

In this paper, a feature extraction-based method for grading cataract severity using retinal images is proposed.

General Classification

Monte Carlo Neural Fictitious Self-Play: Approach to Approximate Nash equilibrium of Imperfect-Information Games

1 code implementation22 Mar 2019 Li Zhang, Wei Wang, Shijian Li, Gang Pan

Experimentally, we demonstrate that the proposed Monte Carlo Neural Fictitious Self Play can converge to approximate Nash equilibrium in games with large-scale search depth while the Neural Fictitious Self Play can't.

Field-aware Neural Factorization Machine for Click-Through Rate Prediction

no code implementations25 Feb 2019 Li Zhang, Weichen Shen, Shijian Li, Gang Pan

This model can have strong second order feature interactive learning ability like Field-aware Factorization Machine, on this basis, deep neural network is used for higher-order feature combination learning.

Click-Through Rate Prediction Feature Engineering +1

Depth creates no more spurious local minima

no code implementations28 Jan 2019 Li Zhang

We show that for any convex differentiable loss, a deep linear network has no spurious local minima as long as it is true for the two layer case.

Learn to Interpret Atari Agents

1 code implementation29 Dec 2018 Zhao Yang, Song Bai, Li Zhang, Philip H. S. Torr

In contrast to previous a-posteriori methods of visualizing DeepRL policies, we propose an end-to-end trainable framework based on Rainbow, a representative Deep Q-Network (DQN) agent.

Decision Making

Fast Online Object Tracking and Segmentation: A Unifying Approach

3 code implementations CVPR 2019 Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H. S. Torr

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach.

Real-Time Visual Tracking Semi-Supervised Semantic Segmentation +2

Automated Segmentation of Cervical Nuclei in Pap Smear Images using Deformable Multi-path Ensemble Model

1 code implementation3 Dec 2018 Jie Zhao, Quanzheng Li, Xiang Li, Hongfeng Li, Li Zhang

Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image.

Medical Image Segmentation

Deep Learning based Pedestrian Detection at Distance in Smart Cities

no code implementations18 Nov 2018 Ranjith K Dinakaran, Philip Easom, Ahmed Bouridane, Li Zhang, Richard Jiang, Fozia Mehboob, Abdul Rauf

Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test.

Pedestrian Detection

Unsupervised Learnable Sinogram Inpainting Network (SIN) for Limited Angle CT reconstruction

no code implementations9 Nov 2018 Ji Zhao, Zhiqiang Chen, Li Zhang, Xin Jin

In this paper, we propose a sinogram inpainting network (SIN) to solve limited-angle CT reconstruction problem, which is a very challenging ill-posed issue and of great interest for several clinical applications.

Medical Physics Image and Video Processing

Differentially Private False Discovery Rate Control

no code implementations11 Jul 2018 Cynthia Dwork, Weijie J. Su, Li Zhang

Differential privacy provides a rigorous framework for privacy-preserving data analysis.

Two-sample testing

Improving Text-to-SQL Evaluation Methodology

1 code implementation ACL 2018 Catherine Finegan-Dollak, Jonathan K. Kummerfeld, Li Zhang, Karthik Ramanathan, Sesh Sadasivam, Rui Zhang, Dragomir Radev

Second, we show that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries; therefore, we propose a complementary dataset split for evaluation of future work.

SQL Parsing Text-To-Sql

Multi-Label Transfer Learning for Multi-Relational Semantic Similarity

no code implementations SEMEVAL 2019 Li Zhang, Steven R. Wilson, Rada Mihalcea

Multi-relational semantic similarity datasets define the semantic relations between two short texts in multiple ways, e. g., similarity, relatedness, and so on.

Multi-Task Learning Semantic Similarity +1

In-Orbit Instrument Performance Study and Calibration for POLAR Polarization Measurements

1 code implementation19 May 2018 Zheng-Heng Li, Merlin Kole, Jian-Chao Sun, Li-Ming Song, Nicolas Produit, Bo-Bing Wu, Tianwei Bao, Tancredi Bernasconi, Franck Cadoux, Yongwei Dong, Minzi Feng, Neal Gauvin, Wojtek Hajdas, Hancheng Li, Lu Li, Xin Liu, Radoslaw Marcinkowski, Martin Pohl, Dominik K. Rybka, Haoli Shi, Jacek Szabelski, Teresa Tymieniecka, Ruijie Wang, Yuanhao Wang, Xing Wen, Xin Wu, Shao-Lin Xiong, Anna Zwolinska, Li Zhang, Lai-Yu Zhang, Shuang-Nan Zhang, Yong-Jie Zhang, Yi Zhao

POLAR is a compact space-borne detector designed to perform reliable measurements of the polarization for transient sources like Gamma-Ray Bursts in the energy range 50-500keV.

Instrumentation and Methods for Astrophysics High Energy Physics - Experiment Instrumentation and Detectors

Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity

no code implementations20 Apr 2018 Li Zhang, Steven R. Wilson, Rada Mihalcea

Sentence encoders, which produce sentence embeddings using neural networks, are typically evaluated by how well they transfer to downstream tasks.

Natural Language Understanding Semantic Similarity +3

Cascaded multi-scale and multi-dimension convolutional neural network for stereo matching

no code implementations26 Mar 2018 Haihua Lu, Hai Xu, Li Zhang, Yong Zhao

Firstly, we propose a new multi-scale matching cost computation sub-network, in which two different sizes of receptive fields are implemented parallelly.

Stereo Matching Stereo Matching Hand

Algorithmic Collusion in Cournot Duopoly Market: Evidence from Experimental Economics

no code implementations21 Feb 2018 Nan Zhou, Li Zhang, Shijian Li, Zhijian Wang

In application, we hope, the frameworks, the algorithm design as well as the experiment environment illustrated in this work, can be an incubator or a test bed for researchers and policymakers to handle the emerging algorithmic collusion.

Learning to Compare: Relation Network for Few-Shot Learning

9 code implementations CVPR 2018 Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, Timothy M. Hospedales

Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.

Few-Shot Image Classification Zero-Shot Learning

Learning Differentially Private Recurrent Language Models

no code implementations ICLR 2018 H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy.

IBM Deep Learning Service

2 code implementations18 Sep 2017 Bishwaranjan Bhattacharjee, Scott Boag, Chandani Doshi, Parijat Dube, Ben Herta, Vatche Ishakian, K. R. Jayaram, Rania Khalaf, Avesh Krishna, Yu Bo Li, Vinod Muthusamy, Ruchir Puri, Yufei Ren, Florian Rosenberg, Seetharami R. Seelam, Yandong Wang, Jian Ming Zhang, Li Zhang

Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision.

Distributed, Parallel, and Cluster Computing

On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches

no code implementations26 Aug 2017 Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Nicolas Papernot, Kunal Talwar, Li Zhang

The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy.

Actor-Critic Sequence Training for Image Captioning

no code implementations29 Jun 2017 Li Zhang, Flood Sung, Feng Liu, Tao Xiang, Shaogang Gong, Yongxin Yang, Timothy M. Hospedales

Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing.

Image Captioning

Learning to Learn: Meta-Critic Networks for Sample Efficient Learning

no code implementations29 Jun 2017 Flood Sung, Li Zhang, Tao Xiang, Timothy Hospedales, Yongxin Yang

We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples.

Meta-Learning Transfer Learning

Classification of Neurological Gait Disorders Using Multi-task Feature Learning

no code implementations8 Dec 2016 Ioannis Papavasileiou, Wenlong Zhang, Xin Wang, Jinbo Bi, Li Zhang, Song Han

An advanced machine learning method, multi-task feature learning (MTFL), is used to jointly train classification models of a subject's gait in three classes, post-stroke, PD and healthy gait.

General Classification

Spatially Adaptive Computation Time for Residual Networks

1 code implementation CVPR 2017 Michael Figurnov, Maxwell D. Collins, Yukun Zhu, Li Zhang, Jonathan Huang, Dmitry Vetrov, Ruslan Salakhutdinov

This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image.

General Classification Image Classification +2

GaDei: On Scale-up Training As A Service For Deep Learning

no code implementations18 Nov 2016 Wei Zhang, Minwei Feng, Yunhui Zheng, Yufei Ren, Yandong Wang, Ji Liu, Peng Liu, Bing Xiang, Li Zhang, Bo-Wen Zhou, Fei Wang

By evaluating the NLC workloads, we show that only the conservative hyper-parameter setup (e. g., small mini-batch size and small learning rate) can guarantee acceptable model accuracy for a wide range of customers.

Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning

no code implementations29 Aug 2016 Yao Sui, Ziming Zhang, Guanghui Wang, Yafei Tang, Li Zhang

By exploiting the anisotropy of the filter response, three sparsity related loss functions are proposed to alleviate the overfitting issue of previous methods and improve the overall tracking performance.

Real-Time Visual Tracking

Tracking Completion

no code implementations29 Aug 2016 Yao Sui, Guanghui Wang, Yafei Tang, Li Zhang

A fundamental component of modern trackers is an online learned tracking model, which is typically modeled either globally or locally.

Matrix Completion

Deep Learning with Differential Privacy

18 code implementations1 Jul 2016 Martín Abadi, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains.

Discriminative Low-Rank Tracking

no code implementations ICCV 2015 Yao Sui, Yafei Tang, Li Zhang

Good tracking performance is in general attributed to accurate representation over previously obtained targets or reliable discrimination between the target and the surrounding background.

Nearly Optimal Private LASSO

no code implementations NeurIPS 2015 Kunal Talwar, Abhradeep Guha Thakurta, Li Zhang

In addition, we show that this error bound is nearly optimal amongst all differentially private algorithms.

Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry

1 code implementation20 Nov 2014 Kunal Talwar, Abhradeep Thakurta, Li Zhang

In addition, we show that when the loss function is Lipschitz with respect to the $\ell_1$ norm and $\mathcal{C}$ is $\ell_1$-bounded, a differentially private version of the Frank-Wolfe algorithm gives error bounds of the form $\tilde{O}(n^{-2/3})$.

Nonparametric Context Modeling of Local Appearance for Pose- and Expression-Robust Facial Landmark Localization

no code implementations CVPR 2014 Brandon M. Smith, Jonathan Brandt, Zhe Lin, Li Zhang

We propose a data-driven approach to facial landmark localization that models the correlations between each landmark and its surrounding appearance features.

Face Alignment

Analyze Gauss: Optimal Bounds for Privacy-Preserving Principal Component Analysis

1 code implementation1 May 2014 Cynthia Dwork, Kunal Talwar, Abhradeep Thakurta, Li Zhang

We show that the well-known, but misnamed, randomized response algorithm, with properly tuned parameters, provides a nearly optimal additive quality gap compared to the best possible singular subspace of A.

Exemplar-Based Face Parsing

no code implementations CVPR 2013 Brandon M. Smith, Li Zhang, Jonathan Brandt, Zhe Lin, Jianchao Yang

Given a test image, our algorithm first selects a subset of exemplar images from the database, Our algorithm then computes a nonrigid warp for each exemplar image to align it with the test image.

Face Alignment Face Parsing +1

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