Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Hang Xu

Hang Xu

Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation


May 27, 2021
Lewei Yao, Renjie Pi, Hang Xu, Wei Zhang, Zhenguo Li, Tong Zhang

Figure 1 for Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Figure 2 for Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Figure 3 for Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Figure 4 for Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search


May 25, 2021
Yawen Duan, Xin Chen, Hang Xu, Zewei Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

Figure 1 for TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
Figure 2 for TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
Figure 3 for TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
Figure 4 for TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
* Published at CVPR 2021. 8 pages main paper, 13 pages in total 
  Access Paper or Ask Questions

BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening


May 13, 2021
Wenqi Shao, Hang Yu, Zhaoyang Zhang, Hang Xu, Zhenguo Li, Ping Luo

Figure 1 for BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
Figure 2 for BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
Figure 3 for BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
Figure 4 for BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
* 19 pages, 7 figures, 6 tables 
  Access Paper or Ask Questions

Effective Sparsification of Neural Networks with Global Sparsity Constraint


May 03, 2021
Xiao Zhou, Weizhong Zhang, Hang Xu, Tong Zhang

Figure 1 for Effective Sparsification of Neural Networks with Global Sparsity Constraint
Figure 2 for Effective Sparsification of Neural Networks with Global Sparsity Constraint
Figure 3 for Effective Sparsification of Neural Networks with Global Sparsity Constraint
Figure 4 for Effective Sparsification of Neural Networks with Global Sparsity Constraint

  Access Paper or Ask Questions

Unsupervised Pretraining for Object Detection by Patch Reidentification


Mar 08, 2021
Jian Ding, Enze Xie, Hang Xu, Chenhan Jiang, Zhenguo Li, Ping Luo, Gui-Song Xia

Figure 1 for Unsupervised Pretraining for Object Detection by Patch Reidentification
Figure 2 for Unsupervised Pretraining for Object Detection by Patch Reidentification
Figure 3 for Unsupervised Pretraining for Object Detection by Patch Reidentification
Figure 4 for Unsupervised Pretraining for Object Detection by Patch Reidentification

  Access Paper or Ask Questions

SparseBERT: Rethinking the Importance Analysis in Self-attention


Feb 25, 2021
Han Shi, Jiahui Gao, Xiaozhe Ren, Hang Xu, Xiaodan Liang, Zhenguo Li, James T. Kwok

Figure 1 for SparseBERT: Rethinking the Importance Analysis in Self-attention
Figure 2 for SparseBERT: Rethinking the Importance Analysis in Self-attention
Figure 3 for SparseBERT: Rethinking the Importance Analysis in Self-attention
Figure 4 for SparseBERT: Rethinking the Importance Analysis in Self-attention

  Access Paper or Ask Questions

Segmenting Transparent Object in the Wild with Transformer


Feb 23, 2021
Enze Xie, Wenjia Wang, Wenhai Wang, Peize Sun, Hang Xu, Ding Liang, Ping Luo

Figure 1 for Segmenting Transparent Object in the Wild with Transformer
Figure 2 for Segmenting Transparent Object in the Wild with Transformer
Figure 3 for Segmenting Transparent Object in the Wild with Transformer
Figure 4 for Segmenting Transparent Object in the Wild with Transformer
* Tech. Report 
  Access Paper or Ask Questions

L2E: Learning to Exploit Your Opponent


Feb 18, 2021
Zhe Wu, Kai Li, Enmin Zhao, Hang Xu, Meng Zhang, Haobo Fu, Bo An, Junliang Xing

Figure 1 for L2E: Learning to Exploit Your Opponent
Figure 2 for L2E: Learning to Exploit Your Opponent
Figure 3 for L2E: Learning to Exploit Your Opponent
Figure 4 for L2E: Learning to Exploit Your Opponent

  Access Paper or Ask Questions

DetCo: Unsupervised Contrastive Learning for Object Detection


Feb 09, 2021
Enze Xie, Jian Ding, Wenhai Wang, Xiaohang Zhan, Hang Xu, Zhenguo Li, Ping Luo

Figure 1 for DetCo: Unsupervised Contrastive Learning for Object Detection
Figure 2 for DetCo: Unsupervised Contrastive Learning for Object Detection
Figure 3 for DetCo: Unsupervised Contrastive Learning for Object Detection
Figure 4 for DetCo: Unsupervised Contrastive Learning for Object Detection

  Access Paper or Ask Questions

Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search


Feb 09, 2021
Peidong Liu, Gengwei Zhang, Bochao Wang, Hang Xu, Xiaodan Liang, Yong Jiang, Zhenguo Li

Figure 1 for Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
Figure 2 for Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
Figure 3 for Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
Figure 4 for Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
* Accepted by ICLR2021 Poster 
  Access Paper or Ask Questions

DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning


Feb 05, 2021
Kelly Kostopoulou, Hang Xu, Aritra Dutta, Xin Li, Alexandros Ntoulas, Panos Kalnis

Figure 1 for DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning
Figure 2 for DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning
Figure 3 for DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning
Figure 4 for DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning

  Access Paper or Ask Questions

Trans2Seg: Transparent Object Segmentation with Transformer


Jan 23, 2021
Enze Xie, Wenjia Wang, Wenhai Wang, Peize Sun, Hang Xu, Ding Liang, Ping Luo

Figure 1 for Trans2Seg: Transparent Object Segmentation with Transformer
Figure 2 for Trans2Seg: Transparent Object Segmentation with Transformer
Figure 3 for Trans2Seg: Transparent Object Segmentation with Transformer
Figure 4 for Trans2Seg: Transparent Object Segmentation with Transformer
* Tech. Report 
  Access Paper or Ask Questions

OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research


Dec 19, 2020
Kai Li, Hang Xu, Meng Zhang, Enmin Zhao, Zhe Wu, Junliang Xing, Kaiqi Huang

Figure 1 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research
Figure 2 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research
Figure 3 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research
Figure 4 for OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research

  Access Paper or Ask Questions

Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation


Dec 07, 2020
Gengwei Zhang, Yiming Gao, Hang Xu, Hao Zhang, Zhenguo Li, Xiaodan Liang

Figure 1 for Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
Figure 2 for Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
Figure 3 for Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
Figure 4 for Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
* Accepted by AAAI2021 
  Access Paper or Ask Questions

VEGA: Towards an End-to-End Configurable AutoML Pipeline


Nov 05, 2020
Bochao Wang, Hang Xu, Jiajin Zhang, Chen Chen, Xiaozhi Fang, Ning Kang, Lanqing Hong, Wei Zhang, Yong Li, Zhicheng Liu, Zhenguo Li, Wenzhi Liu, Tong Zhang

Figure 1 for VEGA: Towards an End-to-End Configurable AutoML Pipeline
Figure 2 for VEGA: Towards an End-to-End Configurable AutoML Pipeline
Figure 3 for VEGA: Towards an End-to-End Configurable AutoML Pipeline
Figure 4 for VEGA: Towards an End-to-End Configurable AutoML Pipeline
* AutoML pipeline. Code is open-sourced at https://github.com/huawei-noah/vega 
  Access Paper or Ask Questions

Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation


Oct 30, 2020
Yangxin Wu, Gengwei Zhang, Hang Xu, Xiaodan Liang, Liang Lin

Figure 1 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
Figure 2 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
Figure 3 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
Figure 4 for Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
* NeurIPS2020 
  Access Paper or Ask Questions

Driver Anomaly Detection: A Dataset and Contrastive Learning Approach


Sep 30, 2020
Okan Köpüklü, Jiapeng Zheng, Hang Xu, Gerhard Rigoll

Figure 1 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Figure 2 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Figure 3 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Figure 4 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach

  Access Paper or Ask Questions

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending


Jul 23, 2020
Hang Xu, Shaoju Wang, Xinyue Cai, Wei Zhang, Xiaodan Liang, Zhenguo Li

Figure 1 for CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
Figure 2 for CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
Figure 3 for CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
Figure 4 for CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
* Accepted by ECCV2020 
  Access Paper or Ask Questions

CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search


Jul 22, 2020
Xin Chen, Yawen Duan, Zewei Chen, Hang Xu, Zihao Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

Figure 1 for CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
Figure 2 for CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
Figure 3 for CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
Figure 4 for CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
* Published at ECCV2020 
  Access Paper or Ask Questions

AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling


Jul 18, 2020
Wenshuo Ma, Tingzhong Tian, Hang Xu, Yimin Huang, Zhenguo Li

Figure 1 for AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
Figure 2 for AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
Figure 3 for AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
Figure 4 for AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
* Accepted by ECCV 2020 (spotlight) 
  Access Paper or Ask Questions

JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image


Jul 10, 2020
Linpu Fang, Xingyan Liu, Li Liu, Hang Xu, Wenxiong Kang

Figure 1 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
Figure 2 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
Figure 3 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
Figure 4 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
* Accepted by ECCV2020 as a Spotlight paper 
  Access Paper or Ask Questions

ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection


Mar 03, 2020
Chenhan Jiang, Shaoju Wang, Hang Xu, Xiaodan Liang, Nong Xiao

Figure 1 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
Figure 2 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
Figure 3 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
Figure 4 for ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
* 7 pages, 5 figure, AAAI2020 
  Access Paper or Ask Questions

EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement


Feb 18, 2020
Linpu Fang, Hang Xu, Zhili Liu, Sarah Parisot, Zhenguo Li

Figure 1 for EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
Figure 2 for EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
Figure 3 for EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
Figure 4 for EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
* Accepted by AAAI20 
  Access Paper or Ask Questions

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN


Feb 18, 2020
Hang Xu, Linpu Fang, Xiaodan Liang, Wenxiong Kang, Zhenguo Li

Figure 1 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN
Figure 2 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN
Figure 3 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN
Figure 4 for Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN
* Accepted by AAAI20 
  Access Paper or Ask Questions

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection


Nov 30, 2019
Lewei Yao, Hang Xu, Wei Zhang, Xiaodan Liang, Zhenguo Li

Figure 1 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
Figure 2 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
Figure 3 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
Figure 4 for SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
* Accepted by AAAI 2020 
  Access Paper or Ask Questions