Search Results for author: Yu Liu

Found 169 papers, 62 papers with code

SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map

no code implementations EMNLP 2021 Kangli Zi, Shi Wang, Yu Liu, Jicun Li, Yanan Cao, Cungen Cao

Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English.

Question Answering Sentence Compression

More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning

1 code implementation ECCV 2020 Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia, Ales Leonardis, Tinne Tuytelaars

Since those regularization strategies are mostly associated with classifier outputs, we propose a MUlti-Classifier (MUC) incremental learning paradigm that integrates an ensemble of auxiliary classifiers to estimate more effective regularization constraints.

Incremental Learning

Centralized Cooperative Exploration Policy for Continuous Control Tasks

1 code implementation6 Jan 2023 Chao Li, Chen Gong, Qiang He, Xinwen Hou, Yu Liu

To explicitly encourage exploration in continuous control tasks, we propose CCEP (Centralized Cooperative Exploration Policy), which utilizes underestimation and overestimation of value functions to maintain the capacity of exploration.

Continuous Control

Urban Visual Intelligence: Studying Cities with AI and Street-level Imagery

no code implementations2 Jan 2023 Fan Zhanga, Arianna Salazar Mirandaa, Fábio Duarte, Lawrence Vale, Gary Hack, Yu Liu, Michael Batty, Carlo Ratti

The visual dimension of cities has been a fundamental subject in urban studies, since the pioneering work of scholars such as Sitte, Lynch, Arnheim, and Jacobs.

Hyperbolic Hierarchical Contrastive Hashing

no code implementations17 Dec 2022 Rukai Wei, Yu Liu, Jingkuan Song, Yanzhao Xie, Ke Zhou

To exploit the hierarchical semantic structures in hyperbolic space, we designed the hierarchical contrastive learning algorithm, including hierarchical instance-wise and hierarchical prototype-wise contrastive learning.

Contrastive Learning Retrieval

Dimensionality-Varying Diffusion Process

no code implementations29 Nov 2022 Han Zhang, Ruili Feng, Zhantao Yang, Lianghua Huang, Yu Liu, Yifei Zhang, Yujun Shen, Deli Zhao, Jingren Zhou, Fan Cheng

Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension.

Image Generation

ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

1 code implementation29 Nov 2022 Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.

Decision Making Q-Learning +2

Unsupervised Domain Adaptation GAN Inversion for Image Editing

no code implementations22 Nov 2022 Siyu Xing, Chen Gong, Hewei Guo, Xiao-Yu Zhang, Xinwen Hou, Yu Liu

In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing.

Image Reconstruction Unsupervised Domain Adaptation

DETRs with Collaborative Hybrid Assignments Training

1 code implementation22 Nov 2022 Zhuofan Zong, Guanglu Song, Yu Liu

This new training scheme can easily enhance the encoder's learning ability in end-to-end detectors by training the multiple parallel auxiliary heads supervised by one-to-many label assignments such as ATSS, FCOS, and Faster RCNN.

Ranked #4 on Object Detection on COCO test-dev (using extra training data)

Object Detection set matching

Teach-DETR: Better Training DETR with Teachers

1 code implementation22 Nov 2022 Linjiang Huang, Kaixin Lu, Guanglu Song, Liang Wang, Si Liu, Yu Liu, Hongsheng Li

In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors.

Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network

no code implementations19 Nov 2022 Xiang Wang, Yimin Yang, Zhichang Guo, Zhili Zhou, Yu Liu, Qixiang Pang, Shan Du

First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain.

Image Super-Resolution Transfer Learning

Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network

no code implementations18 Nov 2022 Xiang Wang, Yimin Yang, Qixiang Pang, Xiao Lu, Yu Liu, Shan Du

In this paper, we propose a novel face super-resolution method, namely Semantic Encoder guided Generative Adversarial Face Ultra-Resolution Network (SEGA-FURN) to ultra-resolve an unaligned tiny LR face image to its HR counterpart with multiple ultra-upscaling factors (e. g., 4x and 8x).

Image Super-Resolution

Channel Tracking for RIS-aided mmWave Communications Under High Mobility Scenarios

no code implementations7 Nov 2022 Yu Liu, Ming Chen, Cunhua Pan, Yijin Pan, Yinlu Wang, Yaoming Huang, Tianyang Cao, Jiangzhou Wang

The emerging reconfigurable intelligent surface (RIS) technology is promising for applications in the millimeter wave (mmWave) communication systems to effectively compensate for propagation loss or tackle the blockage issue.

PolyBuilding: Polygon Transformer for End-to-End Building Extraction

no code implementations3 Nov 2022 Yuan Hu, Zhibin Wang, Zhou Huang, Yu Liu

Given a set of polygon queries, the model learns the relations among them and encodes context information from the image to predict the final set of building polygons with fixed vertex numbers.

Large-batch Optimization for Dense Visual Predictions

1 code implementation20 Oct 2022 Zeyue Xue, Jianming Liang, Guanglu Song, Zhuofan Zong, Liang Chen, Yu Liu, Ping Luo

To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (AGVM), which can train dense visual predictors with very large batch size, enabling several benefits more appealing than prior arts.

Instance Segmentation object-detection +2

Unsupervised Object-Centric Learning with Bi-Level Optimized Query Slot Attention

2 code implementations17 Oct 2022 Baoxiong Jia, Yu Liu, Siyuan Huang

We hope our effort could provide a single home for the design and learning of slot-based models and pave the way for more challenging tasks in object-centric learning.

Image Segmentation Semantic Segmentation +2

DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models

no code implementations16 Oct 2022 Yueqin Yin, Lianghua Huang, Yu Liu, Kaiqi Huang

In this work, we first design a group of mechanisms to simulate generative artifacts of popular generators (i. e., GANs, autoregressive models, and diffusion models), given real images.

Image Generation Image Restoration

SOM-Net: Unrolling the Subspace-based Optimization for Solving Full-wave Inverse Scattering Problems

no code implementations8 Sep 2022 Yu Liu, Hao Zhao, Rencheng Song, Xudong Chen, Chang Li, Xun Chen

The final output of the SOM-Net is the full predicted induced current, from which the scattered field and the permittivity image can also be deduced analytically.

EEG-based Emotion Recognition via Efficient Convolutional Neural Network and Contrastive Learning

no code implementations IEEE Sensors Journal 2022 Chang Li, Xuejuan Lin, Yu Liu, Rencheng Song, Juan Cheng, Xun Chen

To achieve a simple and effective model with supervised learning, we propose an efficient CNN and contrastive learning (ECNN-C) method for EEG-based emotion recognition.

Contrastive Learning EEG +1

Towards Robust Face Recognition with Comprehensive Search

no code implementations29 Aug 2022 Manyuan Zhang, Guanglu Song, Yu Liu, Hongsheng Li

To eliminate the bias of single-aspect research and provide an overall understanding of the face recognition model design, we first carefully design the search space for each aspect, then a comprehensive search method is introduced to jointly search optimal data cleaning, architecture, and loss function design.

Face Recognition Robust Face Recognition

Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization

1 code implementation18 Aug 2022 Xizhe Xue, Dongdong Yu, Lingqiao Liu, Yu Liu, Satoshi Tsutsui, Ying Li, Zehuan Yuan, Ping Song, Mike Zheng Shou

Based on the single-stage instance segmentation framework, we propose a regularization model to predict foreground pixels and use its relation to instance segmentation to construct a cross-task consistency loss.

Autonomous Driving Instance Segmentation +1

Unifying Visual Perception by Dispersible Points Learning

1 code implementation18 Aug 2022 Jianming Liang, Guanglu Song, Biao Leng, Yu Liu

The method, called UniHead, views different visual perception tasks as the dispersible points learning via the transformer encoder architecture.

Instance Segmentation object-detection +3

Reduced Implication-bias Logic Loss for Neuro-Symbolic Learning

no code implementations14 Aug 2022 Haoyuan He, WangZhou Dai, Ming Li, Yu Liu, Yongchang Ma

Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems.

Logical Reasoning

Rethinking Robust Representation Learning Under Fine-grained Noisy Faces

no code implementations8 Aug 2022 Bingqi Ma, Guanglu Song, Boxiao Liu, Yu Liu

To better understand this, we reformulate the noise type of each class in a more fine-grained manner as N-identities|K^C-clusters.

Face Recognition Representation Learning

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

1 code implementation18 Jul 2022 Jihao Liu, Boxiao Liu, Hang Zhou, Hongsheng Li, Yu Liu

In this paper, we propose a novel data augmentation technique TokenMix to improve the performance of vision transformers.

Data Augmentation

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

2 code implementations12 Jul 2022 Jihao Liu, Xin Huang, Guanglu Song, Hongsheng Li, Yu Liu

Finally, we integrate configurable operators and DSMs into a unified search space and search with a Reinforcement Learning-based search algorithm to fully explore the optimal combination of the operators.

Image Classification Neural Architecture Search

DeStripe: A Self2Self Spatio-Spectral Graph Neural Network with Unfolded Hessian for Stripe Artifact Removal in Light-sheet Microscopy

no code implementations27 Jun 2022 Yu Liu, Kurt Weiss, Nassir Navab, Carsten Marr, Jan Huisken, Tingying Peng

Light-sheet fluorescence microscopy (LSFM) is a cutting-edge volumetric imaging technique that allows for three-dimensional imaging of mesoscopic samples with decoupled illumination and detection paths.


A generalized regionalization framework for geographical modelling and its application in spatial regression

1 code implementation19 Jun 2022 Hao Guo, Andre Python, Yu Liu

Models applied to geographic data face a trade-off between producing general results and capturing local variations due to spatial heterogeneity.


Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior

no code implementations28 May 2022 Kai Hu, Yu Liu, Renhe Liu, Wei Lu, Gang Yu, Bin Fu

In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can better preserve the original facial features and avoid excessive fantasy.

Blind Face Restoration Super-Resolution

MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning

1 code implementation26 May 2022 Jihao Liu, Xin Huang, Osamu Yoshie, Yu Liu, Hongsheng Li

In this study, we propose Mixed and Masked Image Modeling (MixMIM), a simple but efficient MIM method that is applicable to various hierarchical Vision Transformers.

Image Classification Object Detection +2

HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding

no code implementations30 Apr 2022 Xiaosong Jia, Penghao Wu, Li Chen, Hongyang Li, Yu Liu, Junchi Yan

One essential task for autonomous driving is to encode the information of a driving scene into vector representations so that the downstream task such as trajectory prediction could perform well.

Autonomous Driving graph construction +1

Dual-Domain Reconstruction Networks with V-Net and K-Net for fast MRI

no code implementations11 Mar 2022 Xiaohan Liu, Yanwei Pang, Ruiqi Jin, Yu Liu, ZhenChang Wang

Purpose: To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data.

Image Reconstruction

Mapping evolving population geography in China

1 code implementation4 Mar 2022 Lei Dong, Rui Du, Yu Liu

China's demographic changes have important global economic and geopolitical implications.

Meta Knowledge Distillation

no code implementations16 Feb 2022 Jihao Liu, Boxiao Liu, Hongsheng Li, Yu Liu

Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations.

Data Augmentation Knowledge Distillation

UniFormer: Unifying Convolution and Self-attention for Visual Recognition

5 code implementations24 Jan 2022 Kunchang Li, Yali Wang, Junhao Zhang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning.

Image Classification object-detection +5

Pedestrian Dead Reckoning System using Quasi-static Magnetic Field Detection

no code implementations24 Jan 2022 Liqiang Zhang, Kai Guo, Yu Liu

Kalman filter-based Inertial Navigation System (INS) is a reliable and efficient method to estimate the position of a pedestrian indoors.

UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning

2 code implementations12 Jan 2022 Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 9% and 71. 2% top-1 accuracy respectively.

Representation Learning

Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings

no code implementations3 Jan 2022 Kai Wang, Yu Liu, Quan Z. Sheng

Knowledge graph embedding (KGE) has shown great potential in automatic knowledge graph (KG) completion and knowledge-driven tasks.

Knowledge Graph Embedding Knowledge Graph Embeddings

Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way

1 code implementation CVPR 2022 Qi Jia, Shuilian Yao, Yu Liu, Xin Fan, Risheng Liu, Zhongxuan Luo

To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion.

object-detection Object Detection

Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition

no code implementations22 Dec 2021 Qingyuan Gong, Yu Liu, Liqiang Zhang, Renhe Liu

Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance.

Visual Place Recognition

Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution

1 code implementation9 Dec 2021 Yunpeng Bai, Chen Gong, Bin Zhang, Guoliang Fan, Xinwen Hou, Yu Liu

HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards.

reinforcement-learning reinforcement Learning +4

Overcome Anterograde Forgetting with Cycled Memory Networks

no code implementations4 Dec 2021 Jian Peng, Dingqi Ye, Bo Tang, Yinjie Lei, Yu Liu, Haifeng Li

This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning.

Transfer Learning

Optimization of RIS Configurations for Multiple-RIS-Aided mmWave Positioning Systems based on CRLB Analysis

no code implementations28 Nov 2021 Yu Liu, Sheng Hong, Cunhua Pan, Yinlu Wang, Yijin Pan, Ming Chen

Reconfigurable intelligent surface (RIS) is a promising technology for future millimeter-wave (mmWave) communication systems.

Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing

no code implementations24 Nov 2021 Yu Liu, Mingbo Zhao, Zhao Zhang, Haijun Zhang, Shuicheng Yan

Based on this dataset, we then propose the Arbitrary Virtual Try-On Network (AVTON) that is utilized for all-type clothes, which can synthesize realistic try-on images by preserving and trading off characteristics of the target clothes and the reference person.

Geometric Matching Virtual Try-on

Self-slimmed Vision Transformer

1 code implementation24 Nov 2021 Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu

Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.

Knowledge Distillation

A Bayesian Model for Online Activity Sample Sizes

no code implementations23 Nov 2021 Thomas Richardson, Yu Liu, James McQueen, Doug Hains

Given observations on the number of unique users participating in an initial period, we present a simple but novel Bayesian method for predicting the number of additional individuals who will participate during a subsequent period.

Reviewing continual learning from the perspective of human-level intelligence

no code implementations23 Nov 2021 Yifan Chang, Wenbo Li, Jian Peng, Bo Tang, Yu Kang, Yinjie Lei, Yuanmiao Gui, Qing Zhu, Yu Liu, Haifeng Li

Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.

Continual Learning

Learning by Active Forgetting for Neural Networks

no code implementations21 Nov 2021 Jian Peng, Xian Sun, Min Deng, Chao Tao, Bo Tang, Wenbo Li, Guohua Wu, QingZhu, Yu Liu, Tao Lin, Haifeng Li

This paper presents a learning model by active forgetting mechanism with artificial neural networks.

INTERN: A New Learning Paradigm Towards General Vision

no code implementations16 Nov 2021 Jing Shao, Siyu Chen, Yangguang Li, Kun Wang, Zhenfei Yin, Yinan He, Jianing Teng, Qinghong Sun, Mengya Gao, Jihao Liu, Gengshi Huang, Guanglu Song, Yichao Wu, Yuming Huang, Fenggang Liu, Huan Peng, Shuo Qin, Chengyu Wang, Yujie Wang, Conghui He, Ding Liang, Yu Liu, Fengwei Yu, Junjie Yan, Dahua Lin, Xiaogang Wang, Yu Qiao

Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.

Spatio-Temporal Urban Knowledge Graph Enabled Mobility Prediction

no code implementations1 Nov 2021 Huandong Wang, Qiaohong Yu, Yu Liu, Depeng Jin, Yong Li

Further, a complex embedding model with elaborately designed scoring functions is proposed to measure the plausibility of facts in STKG to solve the knowledge graph completion problem, which considers temporal dynamics of the mobility patterns and utilizes PoI categories as the auxiliary information and background knowledge.

Knowledge Graph Completion

Knowledge-driven Site Selection via Urban Knowledge Graph

no code implementations1 Nov 2021 Yu Liu, Jingtao Ding, Yong Li

Specifically, motivated by distilled knowledge and rich semantics in KG, we firstly construct an urban KG (UrbanKG) with cities' key elements and semantic relationships captured.

Feature Engineering

RelationRS: Relationship Representation Network for Object Detection in Aerial Images

no code implementations13 Oct 2021 Zhiming Liu, Xuefei Zhang, Chongyang Liu, Hao Wang, Chao Sun, Bin Li, Weifeng Sun, Pu Huang, Qingjun Li, Yu Liu, Haipeng Kuang, Jihong Xiu

To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution.

object-detection Object Detection In Aerial Images

Rectifying the Data Bias in Knowledge Distillation

no code implementations ICCV 2021 Boxiao Liu, Shenghan Zhang, Guanglu Song, Haihang You, Yu Liu

In this paper, we first quantitatively define the uniformity of the sampled data for training, providing a unified view for methods that learn from biased data.

 Ranked #1 on Face Verification on IJB-C (training dataset metric)

Face Recognition Face Verification +3

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

no code implementations8 Oct 2021 Jihao Liu, Hongsheng Li, Guanglu Song, Xin Huang, Yu Liu

Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks.

Image Classification object-detection +2

Self-Slimming Vision Transformer

no code implementations29 Sep 2021 Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu

Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.

Knowledge Distillation

The $f$-Divergence Reinforcement Learning Framework

no code implementations24 Sep 2021 Chen Gong, Qiang He, Yunpeng Bai, Zhou Yang, Xiaoyu Chen, Xinwen Hou, Xianjie Zhang, Yu Liu, Guoliang Fan

In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards.

Decision Making Mathematical Proofs +2

LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders

no code implementations22 Sep 2021 Xiaoyu Chen, Chen Gong, Qiang He, Xinwen Hou, Yu Liu

Variational autoencoders (VAEs), as an important aspect of generative models, have received a lot of research interests and reached many successful applications.

Image Generation

Spatio-temporal Parking Behaviour Forecasting and Analysis Before and During COVID-19

no code implementations15 Aug 2021 Shuhui Gong, Xiaopeng Mo, Rui Cao, Yu Liu, Wei Tu, Ruibin Bai

Parking demand forecasting and behaviour analysis have received increasing attention in recent years because of their critical role in mitigating traffic congestion and understanding travel behaviours.

Epidemiology graph construction +1

Iterative Self-consistent Parallel Magnetic Resonance Imaging Reconstruction based on Nonlocal Low-Rank Regularization

no code implementations10 Aug 2021 Ting Pan, Jizhong Duan, Junfeng Wang, Yu Liu

Recent methods have exploited the nonlocal self-similarity (NSS) of images by imposing nonlocal low-rankness of similar patches to achieve a superior performance.

Unified Regularity Measures for Sample-wise Learning and Generalization

no code implementations9 Aug 2021 Chi Zhang, Xiaoning Ma, Yu Liu, Le Wang, Yuanqi SU, Yuehu Liu

Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes.

Learning Theory Memorization

Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle

no code implementations27 Jul 2021 Jie Li, Sheng Zhang, Kai Han, Xia Yuan, Chunxia Zhao, Yu Liu

UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.

Keypoint Detection

Curvature Graph Neural Network

no code implementations30 Jun 2021 Haifeng Li, Jun Cao, Jiawei Zhu, Yu Liu, Qing Zhu, Guohua Wu

And we propose Curvature Graph Neural Network (CGNN), which effectively improves the adaptive locality ability of GNNs by leveraging the structural property of graph curvature.

Node Classification

Communication Efficient SGD via Gradient Sampling With Bayes Prior

no code implementations CVPR 2021 Liuyihan Song, Kang Zhao, Pan Pan, Yu Liu, Yingya Zhang, Yinghui Xu, Rong Jin

Different from all of them, we regard large and small gradients selection as the exploitation and exploration of gradient information, respectively.

Image Classification object-detection +2

FNAS: Uncertainty-Aware Fast Neural Architecture Search

no code implementations25 May 2021 Jihao Liu, Ming Zhang, Yangting Sun, Boxiao Liu, Guanglu Song, Yu Liu, Hongsheng Li

Further, an architecture knowledge pool together with a block similarity function is proposed to utilize parameter knowledge and reduces the searching time by 2 times.

Fairness Neural Architecture Search

A Novel Binocular Eye-Tracking SystemWith Stereo Stimuli for 3D Gaze Estimation

no code implementations25 Apr 2021 Jinglin Sun, Zhipeng Wu, Han Wang, Peiguang Jing, Yu Liu

However, most current eye trackers focus on 2D point of gaze (PoG) estimation and cannot provide accurate gaze depth. Concerning future applications such as HCI with 3D displays, we propose a novel binocular eye tracking device with stereo stimuli to provide highly accurate 3D PoG estimation.

Depth Estimation Gaze Estimation

Role-Aware Modeling for N-ary Relational Knowledge Bases

1 code implementation20 Apr 2021 Yu Liu, Quanming Yao, Yong Li

N-ary relational knowledge bases (KBs) represent knowledge with binary and beyond-binary relational facts.

Knowledge Graphs

Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval

no code implementations11 Apr 2021 Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew

Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy.

Cross-Modal Retrieval Retrieval

Self-supervised Video Representation Learning by Context and Motion Decoupling

1 code implementation CVPR 2021 Lianghua Huang, Yu Liu, Bin Wang, Pan Pan, Yinghui Xu, Rong Jin

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias.

Action Recognition motion prediction +3

Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

1 code implementation CVPR 2021 Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew

In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains.

Incremental Learning Person Re-Identification

Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning

no code implementations9 Feb 2021 Yu Liu, Lianghua Huang, Pan Pan, Bin Wang, Yinghui Xu, Rong Jin

However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy.

Classification General Classification +1

Deep Learning for Instance Retrieval: A Survey

no code implementations27 Jan 2021 Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.

Content-Based Image Retrieval Instance Search +1

Fast MNAS: Uncertainty-aware Neural Architecture Search with Lifelong Learning

no code implementations1 Jan 2021 Jihao Liu, Yangting Sun, Ming Zhang, Boxiao Liu, Yu Liu

Further, a life-long knowledge pool together with a block similarity function is proposed to utilize the lifelong parameter knowledge and reduces the searching time by 2 times.

Fairness Neural Architecture Search

Self-supervised Temporal Learning

no code implementations1 Jan 2021 Hao Shao, Yu Liu, Hongsheng Li

Inspired by spatial-based contrastive SSL, we show that significant improvement can be achieved by a proposed temporal-based contrastive learning approach, which includes three novel and efficient modules: temporal augmentations, temporal memory bank and SSTL loss.

Contrastive Learning Retrieval +3

Switchable K-Class Hyperplanes for Noise-Robust Representation Learning

no code implementations ICCV 2021 Boxiao Liu, Guanglu Song, Manyuan Zhang, Haihang You, Yu Liu

When collaborated with the popular ArcFace on million-level data representation learning, we found that the switchable manner in SKH can effectively eliminate the gradient conflict generated by real-world label noise on a single K-class hyperplane.

Model Optimization Representation Learning

Precision test of statistical dynamics with state-to-state ultracold chemistry

no code implementations31 Dec 2020 Yu Liu, Ming-Guang Hu, Matthew A. Nichols, Dongzheng Yang, Daiqian Xie, Hua Guo, Kang-Kuen Ni

Chemical reactions represent a class of quantum problems that challenge both the current theoretical understanding and computational capabilities.

Chemical Physics Atomic Physics Quantum Physics

High Fermi velocities and small cyclotron masses in LaAlGe

no code implementations9 Dec 2020 Zhixiang Hu, Qianheng Du, Yu Liu, D. Graf, C. Petrovic

We report quantum oscillation measurements of LaAlGe, a Lorentz-violating type-II Weyl semimetal with tilted Weyl cones.

Mesoscale and Nanoscale Physics Materials Science

Electronic properties of InAs/EuS/Al hybrid nanowires

no code implementations12 Nov 2020 Chun-Xiao Liu, Sergej Schuwalow, Yu Liu, Kostas Vilkelis, A. L. R. Manesco, P. Krogstrup, Michael Wimmer

We study the electronic properties of InAs/EuS/Al heterostructures as explored in a recent experiment [S. Vaitiekenas \emph{et al.}, Nat.

Mesoscale and Nanoscale Physics

On the Exploration of Incremental Learning for Fine-grained Image Retrieval

1 code implementation15 Oct 2020 Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker, Michael Lew

On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.

Image Retrieval Incremental Learning +1

MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph Embeddings

no code implementations14 Oct 2020 Kai Wang, Yu Liu, Qian Ma, Quan Z. Sheng

Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs).

Knowledge Distillation Knowledge Graph Embedding +2

Image Retrieval for Structure-from-Motion via Graph Convolutional Network

no code implementations17 Sep 2020 Shen Yan, Yang Pen, Shiming Lai, Yu Liu, Maojun Zhang

Conventional image retrieval techniques for Structure-from-Motion (SfM) suffer from the limit of effectively recognizing repetitive patterns and cannot guarantee to create just enough match pairs with high precision and high recall.

Image Retrieval Retrieval

Discriminability Distillation in Group Representation Learning

no code implementations ECCV 2020 Manyuan Zhang, Guanglu Song, Hang Zhou, Yu Liu

We show the discrimiability knowledge has good properties that can be distilled by a light-weight distillation network and can be generalized on the unseen target set.

Representation Learning

Single Cell Transcriptome Research in Human Placenta

no code implementations7 Aug 2020 Hui Li, Qianhui Huang, Yu Liu, Lana X Garmire

Human placenta is a complex and heterogeneous organ interfacing between the mother and the fetus that supports fetal development.

Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification

1 code implementation6 Aug 2020 Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew

To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.

Disentanglement Person Re-Identification +2

Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020

no code implementations20 Jul 2020 Haisheng Su, Jinyuan Feng, Hao Shao, Zhenyu Jiang, Manyuan Zhang, Wei Wu, Yu Liu, Hongsheng Li, Junjie Yan

Specifically, in order to generate high-quality proposals, we consider several factors including the video feature encoder, the proposal generator, the proposal-proposal relations, the scale imbalance, and ensemble strategy.

Temporal Action Localization

Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases

1 code implementation8 Jul 2020 Yu Liu, Quanming Yao, Yong Li

With the rapid development of knowledge bases (KBs), link prediction task, which completes KBs with missing facts, has been broadly studied in especially binary relational KBs (a. k. a knowledge graph) with powerful tensor decomposition related methods.

Link Prediction Tensor Decomposition

1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020

1 code implementation16 Jun 2020 Siyu Chen, Junting Pan, Guanglu Song, Manyuan Zhang, Hao Shao, Ziyi Lin, Jing Shao, Hongsheng Li, Yu Liu

This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.

Spatio-Temporal Action Localization Temporal Action Localization

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

3 code implementations CVPR 2021 Junting Pan, Siyu Chen, Mike Zheng Shou, Yu Liu, Jing Shao, Hongsheng Li

We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.

Action Detection Action Recognition +2

A novel multimodal approach for hybrid brain-computer interface

1 code implementation25 Apr 2020 Zhe Sun, Zihao Huang, Feng Duan, Yu Liu

It has been already shown in literature that the hybrid of EEG and NIRS has better results than their respective individual signals.

Human-Computer Interaction Signal Processing

Change Detection in Heterogeneous Optical and SAR Remote Sensing Images via Deep Homogeneous Feature Fusion

no code implementations8 Apr 2020 Xiao Jiang, Gang Li, Yu Liu, Xiao-Ping Zhang, You He

To solve this problem, this paper presents a new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST).

Change Detection Style Transfer

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

1 code implementation CVPR 2020 Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan

In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.

3D Semantic Scene Completion from a single RGB image

DPGN: Distribution Propagation Graph Network for Few-shot Learning

1 code implementation CVPR 2020 Ling Yang, Liangliang Li, Zilun Zhang, Xinyu Zhou, Erjin Zhou, Yu Liu

To combine the distribution-level relations and instance-level relations for all examples, we construct a dual complete graph network which consists of a point graph and a distribution graph with each node standing for an example.

Few-Shot Learning

Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images

1 code implementation CVPR 2020 Hang Zhou, Jihao Liu, Ziwei Liu, Yu Liu, Xiaogang Wang

Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods.

3D Face Modelling Data Augmentation +1

Revisiting the Sibling Head in Object Detector

2 code implementations CVPR 2020 Guanglu Song, Yu Liu, Xiaogang Wang

The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years.

Disentanglement General Classification +3

KPNet: Towards Minimal Face Detector

no code implementations17 Mar 2020 Guanglu Song, Yu Liu, Yuhang Zang, Xiaogang Wang, Biao Leng, Qingsheng Yuan

The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors.

Face Detection

1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation

2 code implementations17 Mar 2020 Yu Liu, Guanglu Song, Yuhang Zang, Yan Gao, Enze Xie, Junjie Yan, Chen Change Loy, Xiaogang Wang

Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.

General Classification Instance Segmentation +4

Top-1 Solution of Multi-Moments in Time Challenge 2019

1 code implementation12 Mar 2020 Manyuan Zhang, Hao Shao, Guanglu Song, Yu Liu, Junjie Yan

In this technical report, we briefly introduce the solutions of our team 'Efficient' for the Multi-Moments in Time challenge in ICCV 2019.

Action Recognition Video Understanding

3D Gated Recurrent Fusion for Semantic Scene Completion

no code implementations17 Feb 2020 Yu Liu, Jie Li, Qingsen Yan, Xia Yuan, Chunxia Zhao, Ian Reid, Cesar Cadena

This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.

3D Semantic Scene Completion Scene Understanding

Temporal Interlacing Network

4 code implementations17 Jan 2020 Hao Shao, Shengju Qian, Yu Liu

In this way, a heavy temporal model is replaced by a simple interlacing operator.

Optical Flow Estimation Video Understanding

Understanding the mesoscopic scaling patterns within cities

1 code implementation2 Jan 2020 Lei Dong, Zhou Huang, Jiang Zhang, Yu Liu

Understanding quantitative relationships between urban elements is crucial for a wide range of applications.

Physics and Society

Search to Distill: Pearls are Everywhere but not the Eyes

no code implementations CVPR 2020 Yu Liu, Xuhui Jia, Mingxing Tan, Raviteja Vemulapalli, Yukun Zhu, Bradley Green, Xiaogang Wang

Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture.

Ensemble Learning Face Recognition +3

Learning Where to Focus for Efficient Video Object Detection

1 code implementation ECCV 2020 Zhengkai Jiang, Yu Liu, Ceyuan Yang, Jihao Liu, Peng Gao, Qian Zhang, Shiming Xiang, Chunhong Pan

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur.

object-detection Video Object Detection

Gradient Information Guided Deraining with A Novel Network and Adversarial Training

no code implementations9 Oct 2019 Yinglong Wang, Haokui Zhang, Yu Liu, Qinfeng Shi, Bing Zeng

However, the existing methods usually do not have good generalization ability, which leads to the fact that almost all of existing methods have a satisfied performance on removing a specific type of rain streaks, but may have a relatively poor performance on other types of rain streaks.

Rain Removal

Differentiable Kernel Evolution

no code implementations ICCV 2019 Yu Liu, Jihao Liu, Ailing Zeng, Xiaogang Wang

This paper proposes a differentiable kernel evolution (DKE) algorithm to find a better layer-operator for the convolutional neural network.

object-detection Object Detection

Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators using Time Compression Supporting Multiple Spike Codes

no code implementations10 Sep 2019 Changqing Xu, Wenrui Zhang, Yu Liu, Peng Li

Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15. 93x, 13. 88x, and 86. 21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA.

Towards Flops-constrained Face Recognition

1 code implementation2 Sep 2019 Yu Liu, Guanglu Song, Manyuan Zhang, Jihao Liu, Yucong Zhou, Junjie Yan

Large scale face recognition is challenging especially when the computational budget is limited.

Face Recognition

In defense of OSVOS

no code implementations19 Aug 2019 Yu Liu, Yutong Dai, Anh-Dzung Doan, Lingqiao Liu, Ian Reid

Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i. e. online fine-tuning on the target instance.

Depth Estimation Optical Flow Estimation +4

Scalable Place Recognition Under Appearance Change for Autonomous Driving

no code implementations ICCV 2019 Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin, Yu Liu, Thanh-Toan Do, Ian Reid

Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.

Autonomous Driving Visual Place Recognition

Use of OWL and Semantic Web Technologies at Pinterest

no code implementations3 Jul 2019 Rafael S. Gonçalves, Matthew Horridge, Rui Li, Yu Liu, Mark A. Musen, Csongor I. Nyulas, Evelyn Obamos, Dhananjay Shrouty, David Temple

In this paper, we present the engineering of an OWL ontology---the Pinterest Taxonomy---that forms the core of Pinterest's knowledge graph, the Pinterest Taste Graph.

From Caesar Cipher to Unsupervised Learning: A New Method for Classifier Parameter Estimation

no code implementations6 Jun 2019 Yu Liu, Li Deng, Jianshu Chen, Chang Wen Chen

To remove the need for the parallel training corpora has practical significance for real-world applications, and it is one of the main goals of unsupervised learning.

General Classification Language Modelling +3

Extracting human emotions at different places based on facial expressions and spatial clustering analysis

no code implementations6 May 2019 Yuhao Kang, Qingyuan Jia, Song Gao, Xiaohuan Zeng, Yueyao Wang, Stephan Angsuesser, Yu Liu, Xinyue Ye, Teng Fei

In this study, a novel framework for extracting human emotions from large-scale georeferenced photos at different places is proposed.

Knowledge Distillation via Route Constrained Optimization

1 code implementation ICCV 2019 Xiao Jin, Baoyun Peng, Yi-Chao Wu, Yu Liu, Jiaheng Liu, Ding Liang, Xiaolin Hu

However, we find that the representation of a converged heavy model is still a strong constraint for training a small student model, which leads to a high lower bound of congruence loss.

Face Recognition Knowledge Distillation

Conditional Adversarial Generative Flow for Controllable Image Synthesis

no code implementations CVPR 2019 Rui Liu, Yu Liu, Xinyu Gong, Xiaogang Wang, Hongsheng Li

Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions.

Image Generation

RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion

no code implementations CVPR 2019 Jie Li, Yu Liu, Dong Gong, Qinfeng Shi, Xia Yuan, Chunxia Zhao, Ian Reid

RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC).

3D Semantic Scene Completion Scene Labeling

Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes

no code implementations12 Jan 2019 Yu Liu, Lingqiao Liu, Hamid Rezatofighi, Thanh-Toan Do, Qinfeng Shi, Ian Reid

As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years.

object-detection Object Detection

Derivative Estimation in Random Design

no code implementations NeurIPS 2018 Yu Liu, Kris De Brabanter

We propose a nonparametric derivative estimation method for random design without having to estimate the regression function.


RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks

no code implementations24 Nov 2018 Haokui Zhang, Ying Li, Peng Wang, Yu Liu, Chunhua Shen

Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition.

Action Recognition

How to improve the interpretability of kernel learning

no code implementations21 Nov 2018 Jinwei Zhao, Qizhou Wang, YuFei Wang, Yu Liu, Zhenghao Shi, Xinhong Hei

In this paper, a quantitative index of the interpretability is proposed and its rationality is proved, and equilibrium problem between the interpretability and the generalization performance is analyzed.

BIG-bench Machine Learning

How far from automatically interpreting deep learning

no code implementations19 Nov 2018 Jinwei Zhao, Qizhou Wang, YuFei Wang, Xinhong Hei, Yu Liu

In other words, there is a gap between the deep learning model and the cognitive mode.

Gradient Harmonized Single-stage Detector

9 code implementations13 Nov 2018 Buyu Li, Yu Liu, Xiaogang Wang

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i. e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples.

General Classification Object Detection +1

T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction

8 code implementations12 Nov 2018 Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li

However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.

Management Traffic Prediction

Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection

3 code implementations22 Oct 2018 Enqiang Guo, Xinsha Fu, Jiawei Zhu, Min Deng, Yu Liu, Qing Zhu, Haifeng Li

A critical challenge problem of scene change detection is that noisy changes generated by varying illumination, shadows and camera viewpoint make variances of a scene difficult to define and measure since the noisy changes and semantic ones are entangled.

Change Detection Scene Change Detection

Transductive Centroid Projection for Semi-supervised Large-scale Recognition

no code implementations ECCV 2018 Yu Liu, Guanglu Song, Jing Shao, Xiao Jin, Xiaogang Wang

It is inspired by the observation of the weights in classification layer (called extit{anchors}) converge to the central direction of each class in hyperspace.

General Classification

Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network

no code implementations11 Aug 2018 Kai Wang, Yu Liu, Xiujuan Xu, Dan Lin

Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space.

Knowledge Graph Embedding

Talking Face Generation by Adversarially Disentangled Audio-Visual Representation

1 code implementation20 Jul 2018 Hang Zhou, Yu Liu, Ziwei Liu, Ping Luo, Xiaogang Wang

Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech.

Lip Reading Retrieval +2

Improved Techniques for Learning to Dehaze and Beyond: A Collective Study

1 code implementation30 Jun 2018 Yu Liu, Guanlong Zhao, Boyuan Gong, Yang Li, Ritu Raj, Niraj Goel, Satya Kesav, Sandeep Gottimukkala, Zhangyang Wang, Wenqi Ren, DaCheng Tao

Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e. g., object detection) of hazy images.

Image Dehazing Image Restoration +3

MoNet: Deep Motion Exploitation for Video Object Segmentation

no code implementations CVPR 2018 Huaxin Xiao, Jiashi Feng, Guosheng Lin, Yu Liu, Maojun Zhang

In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i. e., frame representation learning and segmentation refinement.

Optical Flow Estimation Representation Learning +3

PAD-Net: A Perception-Aided Single Image Dehazing Network

1 code implementation8 May 2018 Yu Liu, Guanlong Zhao

In this work, we investigate the possibility of replacing the $\ell_2$ loss with perceptually derived loss functions (SSIM, MS-SSIM, etc.)

Image Dehazing MS-SSIM +2

Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy

no code implementations CVPR 2018 Guanglu Song, Yu Liu, Ming Jiang, Yujie Wang, Junjie Yan, Biao Leng

Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone.

Face Detection Philosophy

The artificial ecosystem: number soup (part II)

no code implementations12 Jan 2018 Yu Liu

This paper is a follow-up work about the artificial ecosystem model: number soup (Liu and Sumpter, J. Royal Soc.

Region-based Quality Estimation Network for Large-scale Person Re-identification

no code implementations23 Nov 2017 Guanglu Song, Biao Leng, Yu Liu, Congrui Hetang, Shaofan Cai

One of the major restrictions on the performance of video-based person re-id is partial noise caused by occlusion, blur and illumination.

Large-Scale Person Re-Identification

Transferable Semi-supervised Semantic Segmentation

no code implementations18 Nov 2017 Huaxin Xiao, Yunchao Wei, Yu Liu, Maojun Zhang, Jiashi Feng

The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations.

Semi-Supervised Semantic Segmentation

Learning a Recurrent Residual Fusion Network for Multimodal Matching

no code implementations ICCV 2017 Yu Liu, Yanming Guo, Erwin M. Bakker, Michael S. Lew

A major challenge in matching between vision and language is that they typically have completely different features and representations.

Recurrent Scale Approximation for Object Detection in CNN

1 code implementation ICCV 2017 Yu Liu, Hongyang Li, Junjie Yan, Fangyin Wei, Xiaogang Wang, Xiaoou Tang

To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid.

Face Detection object-detection +1

MLBench: How Good Are Machine Learning Clouds for Binary Classification Tasks on Structured Data?

no code implementations29 Jul 2017 Yu Liu, Hantian Zhang, Luyuan Zeng, Wentao Wu, Ce Zhang

We then compare the performance of the top winning code available from Kaggle with that of running machine learning clouds from both Azure and Amazon on mlbench.

BIG-bench Machine Learning General Classification

Quality Aware Network for Set to Set Recognition

1 code implementation CVPR 2017 Yu Liu, Junjie Yan, Wanli Ouyang

In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage.

Face Verification Person Re-Identification

Unsupervised Sequence Classification using Sequential Output Statistics

no code implementations NeurIPS 2017 Yu Liu, Jianshu Chen, Li Deng

Although it is harder to optimize in its functional form, a stochastic primal-dual gradient method is developed to effectively solve the problem.

Classification General Classification

Learning Deep Features via Congenerous Cosine Loss for Person Recognition

1 code implementation22 Feb 2017 Yu Liu, Hongyang Li, Xiaogang Wang

Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance.

Person Recognition

Zoom Out-and-In Network with Recursive Training for Object Proposal

1 code implementation19 Feb 2017 Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang

In this paper, we propose a zoom-out-and-in network for generating object proposals.

On the Exploration of Convolutional Fusion Networks for Visual Recognition

no code implementations16 Nov 2016 Yu Liu, Yanming Guo, Michael S. Lew

Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules.

Image Retrieval Retrieval +1

Combinatorial Multi-Armed Bandit with General Reward Functions

no code implementations NeurIPS 2016 Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu

Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.

POI: Multiple Object Tracking with High Performance Detection and Appearance Feature

no code implementations19 Oct 2016 Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan

In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting.

Association Multiple Object Tracking

Crafting GBD-Net for Object Detection

1 code implementation8 Oct 2016 Xingyu Zeng, Wanli Ouyang, Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang, Hui Zhou, Xiaogang Wang

The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.

object-detection Object Detection

Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network

no code implementations2 Jun 2016 Yu Liu, Jianlong Fu, Tao Mei, Chang Wen Chen

Second, by using sGRU as basic units, the BMRNN is trained to align the local storylines into the global sequential timeline.

Video Captioning Visual Storytelling

Learning Relaxed Deep Supervision for Better Edge Detection

no code implementations CVPR 2016 Yu Liu, Michael S. Lew

We consider these false positives in the supervision, and are able to achieve high performance for better edge detection.

BSDS500 Edge Detection