Search Results for author: Qiang Wang

Found 57 papers, 20 papers with code

Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks

no code implementations19 May 2022 Qiang Wang, Francisco Roldan Sanchez, Robert McCarthy, David Cordova Bulens, Kevin McGuinness, Noel O'Connor, Manuel Wüthrich, Felix Widmaier, Stefan Bauer, Stephen J. Redmond

Here we extend this method, by modifying the task of Phase 1 of the RRC to require the robot to maintain the cube in a particular orientation, while the cube is moved along the required positional trajectory.

Transfer Learning

FlowFormer: A Transformer Architecture for Optical Flow

1 code implementation30 Mar 2022 Zhaoyang Huang, Xiaoyu Shi, Chao Zhang, Qiang Wang, Ka Chun Cheung, Hongwei Qin, Jifeng Dai, Hongsheng Li

We introduce Optical Flow TransFormer (FlowFormer), a transformer-based neural network architecture for learning optical flow.

Optical Flow Estimation

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

no code implementations29 Mar 2022 Yingjie Cai, Kwan-Yee Lin, Chao Zhang, Qiang Wang, Xiaogang Wang, Hongsheng Li

Specifically, we map a series of related partial point clouds into multiple complete shape and occlusion code pairs and fuse the codes to obtain their representations in the unified latent space.

Point Cloud Completion

Disentangled Representation Learning for Text-Video Retrieval

1 code implementation14 Mar 2022 Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan, Xian-Sheng Hua

Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance.

Ranked #2 on Video Retrieval on MSR-VTT-1kA (using extra training data)

Representation Learning Video Retrieval

RCL: Recurrent Continuous Localization for Temporal Action Detection

no code implementations14 Mar 2022 Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan

Temporal representation is the cornerstone of modern action detection techniques.

Action Detection

2nd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition

no code implementations27 Oct 2021 Haojin Liao, Xiaolin Song, Sicheng Zhao, Shanghang Zhang, Xiangyu Yue, Xingxu Yao, Yueming Zhang, Tengfei Xing, Pengfei Xu, Qiang Wang

The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance between the source and target domains.

Universal Domain Adaptation Unsupervised Domain Adaptation

FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

no code implementations6 Oct 2021 Qiang Wang, Shaohuai Shi, Shizhen Zheng, Kaiyong Zhao, Xiaowen Chu

The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy than traditional hand-crafted feature-based methods.

Disparity Estimation

Solving the Real Robot Challenge using Deep Reinforcement Learning

2 code implementations30 Sep 2021 Robert McCarthy, Francisco Roldan Sanchez, Qiang Wang, David Cordova Bulens, Kevin McGuinness, Noel O'Connor, Stephen J. Redmond

This paper details our winning submission to Phase 1 of the 2021 Real Robot Challenge; a challenge in which a three fingered robot must carry a cube along specified goal trajectories.

reinforcement-learning Robotic Grasping

Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision

no code implementations3 Sep 2021 Zhong Ji, Jin Li, Qiang Wang, Zhongfei Zhang

Furthermore, we explore a collaborative self-supervision idea to leverage pretext tasks and supervised contrastive learning for addressing the feature deviation problem by learning complete and discriminative features for all classes.

Continual Learning Contrastive Learning +1

Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering

no code implementations17 Jun 2021 Wenpeng Xing, Jie Chen, Zaifeng Yang, Qiang Wang

Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence.

Novel View Synthesis

A comparative study of neural network techniques for automatic software vulnerability detection

no code implementations29 Apr 2021 Gaigai Tang, Lianxiao Meng, Shuangyin Ren, Weipeng Cao, Qiang Wang, Lin Yang

To solve this problem, we have conducted extensive experiments to test the performance of the two most typical neural networks (i. e., Bi-LSTM and RVFL) with the two most classical data preprocessing methods (i. e., the vector representation and the program symbolization methods) on software vulnerability detection problems and obtained a series of interesting research conclusions, which can provide valuable guidelines for researchers and engineers.

Vulnerability Detection

Multiple Object Tracking with Correlation Learning

no code implementations CVPR 2021 Qiang Wang, Yun Zheng, Pan Pan, Yinghui Xu

Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features.

Frame Multiple Object Tracking +1

Multi-cell NOMA: Coherent Reconfigurable Intelligent Surfaces Model With Stochastic Geometry

no code implementations3 Mar 2021 Chao Zhang, Wenqiang Yi, Yuanwei Liu, Qiang Wang

Numerical results indicate that 1) although the interference from other cells is enhanced via the RISs, the performance of the RIS-aided user still enhances since the channel quality is strengthened more obviously; and 2) the SIC order can be altered by employing the RISs since the RISs improve the channel quality of the aided user.

Information Theory Information Theory

Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking

1 code implementation21 Jan 2021 Nan Jiang, Kuiran Wang, Xiaoke Peng, Xuehui Yu, Qiang Wang, Junliang Xing, Guorong Li, Jian Zhao, Guodong Guo, Zhenjun Han

The releasing of such a large-scale dataset could be a useful initial step in research of tracking UAVs.

Translation Memory Guided Neural Machine Translation

no code implementations1 Jan 2021 Shaohui Kuang, Heng Yu, Weihua Luo, Qiang Wang

Existing ways either employ extra encoder to encode information from TM or concatenate source sentence and TM sentences as encoder's input.

Language Modelling Machine Translation +1

Hybrid-Regressive Neural Machine Translation

no code implementations1 Jan 2021 Qiang Wang, Heng Yu, Shaohui Kuang, Weihua Luo

Moreover, compared with autoregressive models, HRT can be steadily accelerated 1. 5 times regardless of batch size and device.

14 Machine Translation +1

UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching

no code implementations ICCV 2021 Yamin Mao, Zhihua Liu, Weiming Li, Yuchao Dai, Qiang Wang, Yun-Tae Kim, Hong-Seok Lee

Extensive experiments show that the proposed method achieves the highest ground truth covering ratio compared with other cascade cost volume based stereo matching methods.

Stereo Matching

Layer-Wise Multi-View Learning for Neural Machine Translation

no code implementations COLING 2020 Qiang Wang, Changliang Li, Yue Zhang, Tong Xiao, Jingbo Zhu

In this way, in addition to the topmost encoder layer (referred to as the primary view), we also incorporate an intermediate encoder layer as the auxiliary view.

Machine Translation MULTI-VIEW LEARNING +1

EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual

no code implementations CVPR 2021 Songyan Zhang, Zhicheng Wang, Qiang Wang, Jinshuo Zhang, Gang Wei, Xiaowen Chu

Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption and slow inference speed.

Disparity Estimation Stereo Matching

Automatic Label Correction for the Accurate Edge Detection of Overlapping Cervical Cells

2 code implementations5 Oct 2020 Jiawei Liu, Qiang Wang, Huijie Fan, Shuai Wang, Wentao Li, Yandong Tang, Danbo Wang, Mingyi Zhou, Li Chen

The experiments on the dataset for training show that our automatic label correction algorithm can improve the accuracy of manual labels and further improve the positioning accuracy of overlapping cells with deep learning models.

Cell Segmentation Edge Detection

Rethinking Performance Estimation in Neural Architecture Search

1 code implementation CVPR 2020 Xiawu Zheng, Rongrong Ji, Qiang Wang, Qixiang Ye, Zhenguo Li, Yonghong Tian, Qi Tian

In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space.

Neural Architecture Search

DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks

no code implementations22 Apr 2020 Yikang Zhang, Jian Zhang, Qiang Wang, Zhao Zhong

On one hand, we can reduce the computation cost remarkably while maintaining the performance.

A Graph Joining Greedy Approach to Binary de Bruijn Sequences

1 code implementation21 Apr 2020 Zuling Chang, Martianus Frederic Ezerman, Adamas Aqsa Fahreza, Qiang Wang

Using greedy algorithms to generate de Bruijn sequences is a classical approach that has produced numerous interesting theoretical results.

Information Theory Combinatorics Information Theory

Data Poisoning Attacks on Federated Machine Learning

no code implementations19 Apr 2020 Gan Sun, Yang Cong, Jiahua Dong, Qiang Wang, Ji Liu

To the end, experimental results on real-world datasets show that federated multi-task learning model is very sensitive to poisoning attacks, when the attackers either directly poison the target nodes or indirectly poison the related nodes by exploiting the communication protocol.

Data Poisoning Federated Learning +1

Communication Contention Aware Scheduling of Multiple Deep Learning Training Jobs

no code implementations24 Feb 2020 Qiang Wang, Shaohuai Shi, Canhui Wang, Xiaowen Chu

We thus propose a provable algorithm, AdaDUAL, to efficiently schedule those communication tasks.

Neural Machine Translation with Joint Representation

1 code implementation16 Feb 2020 Yanyang Li, Qiang Wang, Tong Xiao, Tongran Liu, Jingbo Zhu

Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e. g., alignment, the recent Neural Machine Translation (NMT) systems resort to the attention which partially encodes the interaction for efficiency.

Machine Translation Translation

Force-guided High-precision Grasping Control of Fragile and Deformable Objects using sEMG-based Force Prediction

no code implementations5 Feb 2020 Ruoshi Wen, Kai Yuan, Qiang Wang, Shuai Heng, Zhibin Li

Regulating contact forces with high precision is crucial for grasping and manipulating fragile or deformable objects.

Robotics

Adversarial AutoAugment

no code implementations ICLR 2020 Xin-Yu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong

The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization.

Data Augmentation Image Classification

BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search

no code implementations24 Dec 2019 Muyuan Fang, Qiang Wang, Zhao Zhong

Automatic neural architecture search techniques are becoming increasingly important in machine learning area.

Neural Architecture Search

Layer-wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guarantees

no code implementations20 Nov 2019 Shaohuai Shi, Zhenheng Tang, Qiang Wang, Kaiyong Zhao, Xiaowen Chu

To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers.

Distributed Optimization

Anchor Diffusion for Unsupervised Video Object Segmentation

1 code implementation ICCV 2019 Zhao Yang, Qiang Wang, Luca Bertinetto, Weiming Hu, Song Bai, Philip H. S. Torr

Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow.

Ranked #7 on Unsupervised Video Object Segmentation on DAVIS 2016 (using extra training data)

Frame Optical Flow Estimation +3

DyNet: Dynamic Convolution for Accelerating Convolution Neural Networks

no code implementations25 Sep 2019 Kane Zhang, Jian Zhang, Qiang Wang, Zhao Zhong

To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduces 69. 3% FLOPs while maintaining the Mean IoU on segmentation task.

Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training

no code implementations15 Sep 2019 Yuxin Wang, Qiang Wang, Shaohuai Shi, Xin He, Zhenheng Tang, Kaiyong Zhao, Xiaowen Chu

Different from the existing end-to-end benchmarks which only present the training time, We try to investigate the impact of hardware, vendor's software library, and deep learning framework on the performance and energy consumption of AI training.

A Distributed Synchronous SGD Algorithm with Global Top-$k$ Sparsification for Low Bandwidth Networks

1 code implementation14 Jan 2019 Shaohuai Shi, Qiang Wang, Kaiyong Zhao, Zhenheng Tang, Yuxin Wang, Xiang Huang, Xiaowen Chu

Current methods that use AllGather to accumulate the sparse gradients have a communication complexity of $O(kP)$, where $P$ is the number of workers, which is inefficient on low bandwidth networks with a large number of workers.

Vector and Line Quantization for Billion-scale Similarity Search on GPUs

1 code implementation2 Jan 2019 Wei Chen, Jincai Chen, Fuhao Zou, Yuan-Fang Li, Ping Lu, Qiang Wang, Wei Zhao

The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs.

Quantization

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

8 code implementations CVPR 2019 Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan

Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size.

Translation Visual Object Tracking +1

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

The NiuTrans Machine Translation System for WMT18

no code implementations WS 2018 Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao, Jingbo Zhu

This paper describes the submission of the NiuTrans neural machine translation system for the WMT 2018 Chinese ↔ English news translation tasks.

Machine Translation Translation

Visual Tracking via Spatially Aligned Correlation Filters Network

no code implementations ECCV 2018 Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, Steve Maybank

Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background.

Visual Tracking

Distractor-aware Siamese Networks for Visual Object Tracking

1 code implementation ECCV 2018 Zheng Zhu, Qiang Wang, Bo Li, Wei Wu, Junjie Yan, Weiming Hu

During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.

Incremental Learning Visual Object Tracking +1

A Simple and Effective Approach to Coverage-Aware Neural Machine Translation

no code implementations ACL 2018 Yanyang Li, Tong Xiao, Yinqiao Li, Qiang Wang, Changming Xu, Jingbo Zhu

We offer a simple and effective method to seek a better balance between model confidence and length preference for Neural Machine Translation (NMT).

Machine Translation Translation

Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking

2 code implementations CVPR 2018 Qiang Wang, Zhu Teng, Junliang Xing, Jin Gao, Weiming Hu, Stephen Maybank

The RASNet model reformulates the correlation filter within a Siamese tracking framework, and introduces different kinds of the attention mechanisms to adapt the model without updating the model online.

Object Tracking Representation Learning +1

DCFNet: Discriminant Correlation Filters Network for Visual Tracking

5 code implementations13 Apr 2017 Qiang Wang, Jin Gao, Junliang Xing, Mengdan Zhang, Weiming Hu

In this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously.

Object Tracking Visual Tracking

Benchmarking State-of-the-Art Deep Learning Software Tools

no code implementations25 Aug 2016 Shaohuai Shi, Qiang Wang, Pengfei Xu, Xiaowen Chu

We first benchmark the running performance of these tools with three popular types of neural networks on two CPU platforms and three GPU platforms.

Weakly supervised object detection using pseudo-strong labels

no code implementations16 Jul 2016 Ke Yang, Dongsheng Li, Yong Dou, Shaohe Lv, Qiang Wang

Object detection is an import task of computer vision. A variety of methods have been proposed, but methods using the weak labels still do not have a satisfactory result. In this paper, we propose a new framework that using the weakly supervised method's output as the pseudo-strong labels to train a strongly supervised model. One weakly supervised method is treated as black-box to generate class-specific bounding boxes on train dataset. A de-noise method is then applied to the noisy bounding boxes. Then the de-noised pseudo-strong labels are used to train a strongly object detection network. The whole framework is still weakly supervised because the entire process only uses the image-level labels. The experiment results on PASCAL VOC 2007 prove the validity of our framework, and we get result 43. 4% on mean average precision compared to 39. 5% of the previous best result and 34. 5% of the initial method, respectively. And this frame work is simple and distinct, and is promising to be applied to other method easily.

Frame Weakly Supervised Object Detection

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