Search Results for author: Qiang Wang

Found 97 papers, 38 papers with code

Dataset Clustering for Improved Offline Policy Learning

1 code implementation14 Feb 2024 Qiang Wang, Yixin Deng, Francisco Roldan Sanchez, Keru Wang, Kevin McGuinness, Noel O'Connor, Stephen J. Redmond

Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment.

Clustering Continuous Control +2

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

no code implementations3 Feb 2024 Peijie Dong, Lujun Li, Xinglin Pan, Zimian Wei, Xiang Liu, Qiang Wang, Xiaowen Chu

Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the efficacy of zero-cost proxies in various NAS benchmarks.

Neural Architecture Search

MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning

no code implementations14 Dec 2023 Yi Xin, Junlong Du, Qiang Wang, Ke Yan, Shouhong Ding

On the one hand, to maximize the complementarity of tasks with high similarity, we utilize a gradient-driven task grouping method that partitions tasks into several disjoint groups and assign a group-shared MmAP to each group.

Language Modelling Multi-Task Learning +1

VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding

no code implementations14 Dec 2023 Yi Xin, Junlong Du, Qiang Wang, Zhiwen Lin, Ke Yan

Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3. 96%(1. 34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0. 36%) trainable parameters of the pre-trained model.

Scene Understanding Transfer Learning

Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency

1 code implementation3 Oct 2023 Francisco Roldan Sanchez, Qiang Wang, David Cordova Bulens, Kevin McGuinness, Stephen Redmond, Noel O'Connor

Hindsight Experience Replay (HER) is a technique used in reinforcement learning (RL) that has proven to be very efficient for training off-policy RL-based agents to solve goal-based robotic manipulation tasks using sparse rewards.

Reinforcement Learning (RL)

DVI-SLAM: A Dual Visual Inertial SLAM Network

no code implementations25 Sep 2023 Xiongfeng Peng, Zhihua Liu, Weiming Li, Ping Tan, SoonYong Cho, Qiang Wang

Recent deep learning based visual simultaneous localization and mapping (SLAM) methods have made significant progress.

Simultaneous Localization and Mapping

FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs

no code implementations3 Sep 2023 Zhenheng Tang, Yuxin Wang, Xin He, Longteng Zhang, Xinglin Pan, Qiang Wang, Rongfei Zeng, Kaiyong Zhao, Shaohuai Shi, Bingsheng He, Xiaowen Chu

The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPUs from training or deploying LLMs.

Scheduling

FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content

1 code implementation28 Aug 2023 Yang Liu, Cheng Yu, Lei Shang, Yongyi He, Ziheng Wu, Xingjun Wang, Chao Xu, Haoyu Xie, Weida Wang, Yuze Zhao, Lin Zhu, Chen Cheng, Weitao Chen, Yuan YAO, Wenmeng Zhou, Jiaqi Xu, Qiang Wang, Yingda Chen, Xuansong Xie, Baigui Sun

In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.

Attribute Potrait Generation +1

Residual Denoising Diffusion Models

1 code implementation25 Aug 2023 Jiawei Liu, Qiang Wang, Huijie Fan, Yinong Wang, Yandong Tang, Liangqiong Qu

We propose residual denoising diffusion models (RDDM), a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion.

Denoising Image Generation +2

Explicifying Neural Implicit Fields for Efficient Dynamic Human Avatar Modeling via a Neural Explicit Surface

no code implementations7 Aug 2023 Ruiqi Zhang, Jie Chen, Qiang Wang

This paper proposes a technique for efficiently modeling dynamic humans by explicifying the implicit neural fields via a Neural Explicit Surface (NES).

Computational Efficiency

Robust Learning-Based Incipient Slip Detection using the PapillArray Optical Tactile Sensor for Improved Robotic Gripping

no code implementations8 Jul 2023 Qiang Wang, Pablo Martinez Ulloa, Robert Burke, David Cordova Bulens, Stephen J. Redmond

When transferring the trained model to a robotic gripping environment distinct from where the training data was collected, our model maintained robust performance, with a success rate of 96. 8%, providing timely feedback for stabilizing several practical gripping tasks.

Data Augmentation

Improving the Transferability of Time Series Forecasting with Decomposition Adaptation

no code implementations30 Jun 2023 Yan Gao, Yan Wang, Qiang Wang

However, in time series forecasting, it is difficult to obtain enough data, which limits the performance of neural forecasting models.

Multivariate Time Series Forecasting Time Series +1

Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System

1 code implementation27 Jun 2023 Xue-Feng Zhu, Tianyang Xu, Jian Zhao, Jia-Wei Liu, Kai Wang, Gang Wang, Jianan Li, Qiang Wang, Lei Jin, Zheng Zhu, Junliang Xing, Xiao-Jun Wu

Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i. e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance).

FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow

no code implementations8 Jun 2023 Zhaoyang Huang, Xiaoyu Shi, Chao Zhang, Qiang Wang, Yijin Li, Hongwei Qin, Jifeng Dai, Xiaogang Wang, Hongsheng Li

This paper introduces a novel transformer-based network architecture, FlowFormer, along with the Masked Cost Volume AutoEncoding (MCVA) for pretraining it to tackle the problem of optical flow estimation.

Optical Flow Estimation

DiffSketching: Sketch Control Image Synthesis with Diffusion Models

no code implementations30 May 2023 Qiang Wang, Di Kong, Fengyin Lin, Yonggang Qi

Creative sketch is a universal way of visual expression, but translating images from an abstract sketch is very challenging.

Image Generation

Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning

no code implementations20 Mar 2023 Rongxiang Weng, Qiang Wang, Wensen Cheng, Changfeng Zhu, Min Zhang

A contributing factor to this problem is that NMT models trained with the one-to-one paradigm struggle to handle the source diversity phenomenon, where inputs with the same meaning can be expressed differently.

Bilevel Optimization Machine Translation +4

SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning

no code implementations16 Mar 2023 Shuhan Qi, Shuhao Zhang, Qiang Wang, Jiajia Zhang, Jing Xiao, Xuan Wang

In this paper, we propose a scalable value-decomposition exploration (SVDE) method, which includes a scalable training mechanism, intrinsic reward design, and explorative experience replay.

Multi-agent Reinforcement Learning reinforcement-learning +3

A Decoupled Multi-Task Network for Shadow Removal

1 code implementation IEEE Transactions on Multimedia 2023 Jiawei Liu, Qiang Wang, Huijie Fan, Wentao Li, Liangqiong Qu, Yandong Tang

Last, these features are converted to a target shadow-free image, affiliated shadow matte, and shadow image, supervised by multi-task joint loss functions.

Image Reconstruction Image Shadow Removal +1

The RoyalFlush System for the WMT 2022 Efficiency Task

no code implementations3 Dec 2022 Bo Qin, Aixin Jia, Qiang Wang, Jianning Lu, Shuqin Pan, Haibo Wang, Ming Chen

This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task.

Knowledge Distillation Machine Translation +1

Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity

1 code implementation30 Nov 2022 Qingsong Yan, Qiang Wang, Kaiyong Zhao, Bo Li, Xiaowen Chu, Fei Deng

Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable.

Hybrid-Regressive Neural Machine Translation

no code implementations19 Oct 2022 Qiang Wang, Xinhui Hu, Ming Chen

HRT achieves the state-of-the-art BLEU score of 28. 49 on the WMT En-De task and is at least 1. 5x faster than AT, regardless of batch size and device.

Machine Translation Translation

Learning from Students: Online Contrastive Distillation Network for General Continual Learning

1 code implementation Conference 2022 Jin Li, Zhong Ji, Gang Wang, Qiang Wang, Feng Gao

The goal of General Continual Learning (GCL) is to preserve learned knowledge and learn new knowledge with constant memory from an infinite data stream where task boundaries are blurry.

Continual Learning

Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation

no code implementations COLING 2022 Qiang Wang, Rongxiang Weng, Ming Chen

Generally, kNN-MT borrows the off-the-shelf context representation in the translation task, e. g., the output of the last decoder layer, as the query vector of the retrieval task.

Contrastive Learning Machine Translation +2

SphereDepth: Panorama Depth Estimation from Spherical Domain

no code implementations29 Aug 2022 Qingsong Yan, Qiang Wang, Kaiyong Zhao, Bo Li, Xiaowen Chu, Fei Deng

The panorama image can simultaneously demonstrate complete information of the surrounding environment and has many advantages in virtual tourism, games, robotics, etc.

Depth Estimation

Adaptive Target-Condition Neural Network: DNN-Aided Load Balancing for Hybrid LiFi and WiFi Networks

no code implementations9 Aug 2022 Han Ji, Qiang Wang, Stephen J. Redmond, Iman Tavakkolnia, Xiping Wu

In this paper, a novel deep neural network (DNN) structure named adaptive target-condition neural network (A-TCNN) is proposed, which conducts AP selection for one target user upon the condition of other users.

An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation

no code implementations20 Jul 2022 Leiyang Xu, Qiang Wang, Xiaotian Lin, Lin Yuan

This study proposes an efficient framework for the few-shot skeleton-based TAS, including a data augmentation method and an improved model.

Action Segmentation Data Augmentation +2

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

1 code implementation20 Jul 2022 Qiang Wang, Shaohuai Shi, Kaiyong Zhao, Xiaowen Chu

However, existing NAS studies on the dense prediction task, especially stereo matching, still cannot be efficiently and effectively deployed on devices of different computing capabilities.

Image Classification Neural Architecture Search +3

Automatic dataset generation for specific object detection

no code implementations16 Jul 2022 Xiaotian Lin, Leiyang Xu, Qiang Wang

In the past decade, object detection tasks are defined mostly by large public datasets.

Object object-detection +1

SiamMask: A Framework for Fast Online Object Tracking and Segmentation

no code implementations5 Jul 2022 Weiming Hu, Qiang Wang, Li Zhang, Luca Bertinetto, Philip H. S. Torr

In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method.

Multiple Object Tracking Object +5

Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition

no code implementations30 Jun 2022 Lin Yuan, Zhen He, Qiang Wang, Leiyang Xu, Xiang Ma

Human action recognition is a quite hugely investigated area where most remarkable action recognition networks usually use large-scale coarse-grained action datasets of daily human actions as inputs to state the superiority of their networks.

Action Recognition Temporal Action Localization +1

fETSmcs: Feature-based ETS model component selection

1 code implementation26 Jun 2022 Lingzhi Qi, Xixi Li, Qiang Wang, Suling Jia

We evaluate our approach on the widely used forecasting competition data set M4, in terms of both point forecasts and prediction intervals.

Model Selection Prediction Intervals +2

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

1 code implementation19 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, dubbed as 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 implementations CVPR 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

2 code implementations14 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 #9 on Video Retrieval on MSR-VTT-1kA (using extra training data)

Representation Learning Retrieval +1

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

Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks

no code implementations5 Oct 2021 Robert McCarthy, Qiang Wang, Stephen J. Redmond

Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts.

Model-based Reinforcement Learning OpenAI Gym

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 Reinforcement Learning (RL) +1

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

1 code implementation3 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 +2

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.

Multiple Object Tracking Object +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.

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

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 +4

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 +2

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

Local Label Point Correction for Edge Detection of Overlapping Cervical Cells

1 code implementation5 Oct 2020 Jiawei Liu, Huijie Fan, Qiang Wang, Wentao Li, Yandong Tang, Danbo Wang, Mingyi Zhou, Li Chen

The qualitative and quantitative experimental results show that our LLPC can improve the quality of manual labels and the accuracy of overlapping cell edge detection.

Cell Segmentation Edge Detection +2

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.

BIG-bench Machine Learning Data Poisoning +2

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.

Scheduling

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 NMT +1

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 +1

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

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.

Benchmarking

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

13 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.

Object Real-Time Visual Tracking +4

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 Object +2

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 NMT +1

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 Test +1

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.

Benchmarking

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.

Object object-detection +1

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