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 Han Hu

Han Hu

University of Toronto

Semi-Supervised Adversarial Recognition of Refined Window Structures for Inverse Procedural Façade Modeling


Jan 22, 2022
Han Hu, Xinrong Liang, Yulin Ding, Qisen Shang, Bo Xu, Xuming Ge, Min Chen, Ruofei Zhong, Qing Zhu


  Access Paper or Ask Questions

A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model


Dec 29, 2021
Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Han Hu, Xiang Bai

Figure 1 for A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model
Figure 2 for A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model
Figure 3 for A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model
Figure 4 for A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model

  Access Paper or Ask Questions

FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps


Nov 21, 2021
Han Hu, Xiaopeng Jiang, Vijaya Datta Mayyuri, An Chen, Devu M. Shila, Adriaan Larmuseau, Ruoming Jin, Cristian Borcea, NhatHai Phan

Figure 1 for FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps
Figure 2 for FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps
Figure 3 for FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps
Figure 4 for FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps
* The first two authors contributed equally to this work 
  Access Paper or Ask Questions

SimMIM: A Simple Framework for Masked Image Modeling


Nov 18, 2021
Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu

Figure 1 for SimMIM: A Simple Framework for Masked Image Modeling
Figure 2 for SimMIM: A Simple Framework for Masked Image Modeling
Figure 3 for SimMIM: A Simple Framework for Masked Image Modeling
Figure 4 for SimMIM: A Simple Framework for Masked Image Modeling

  Access Paper or Ask Questions

Swin Transformer V2: Scaling Up Capacity and Resolution


Nov 18, 2021
Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo

Figure 1 for Swin Transformer V2: Scaling Up Capacity and Resolution
Figure 2 for Swin Transformer V2: Scaling Up Capacity and Resolution
Figure 3 for Swin Transformer V2: Scaling Up Capacity and Resolution
Figure 4 for Swin Transformer V2: Scaling Up Capacity and Resolution

  Access Paper or Ask Questions

FLSys: Toward an Open Ecosystem for FederatedLearning Mobile Apps


Nov 17, 2021
Han Hu, Xiaopeng Jiang, Vijaya Datta Mayyuri, An Chen, Devu M. Shila, Adriaan Larmuseau, Ruoming Jin, Cristian Borcea, NhatHai Phan

Figure 1 for FLSys: Toward an Open Ecosystem for FederatedLearning Mobile Apps
Figure 2 for FLSys: Toward an Open Ecosystem for FederatedLearning Mobile Apps
Figure 3 for FLSys: Toward an Open Ecosystem for FederatedLearning Mobile Apps
Figure 4 for FLSys: Toward an Open Ecosystem for FederatedLearning Mobile Apps
* The first two authors contributed equally to this work 
  Access Paper or Ask Questions

Bootstrap Your Object Detector via Mixed Training


Nov 04, 2021
Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Stephen Lin, Han Hu, Xiang Bai

Figure 1 for Bootstrap Your Object Detector via Mixed Training
Figure 2 for Bootstrap Your Object Detector via Mixed Training
Figure 3 for Bootstrap Your Object Detector via Mixed Training
Figure 4 for Bootstrap Your Object Detector via Mixed Training
* NeurIPS 2021, Spotlight 
  Access Paper or Ask Questions

Spatial Constraint Generation for Motion Planning in Dynamic Environments


Oct 27, 2021
Han Hu, Peyman Yadmellat

Figure 1 for Spatial Constraint Generation for Motion Planning in Dynamic Environments
Figure 2 for Spatial Constraint Generation for Motion Planning in Dynamic Environments
Figure 3 for Spatial Constraint Generation for Motion Planning in Dynamic Environments
Figure 4 for Spatial Constraint Generation for Motion Planning in Dynamic Environments
* This is the author's version of the paper that's accepted by IROS2021 
  Access Paper or Ask Questions

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning


Oct 11, 2021
Hanzhe Hu, Fangyun Wei, Han Hu, Qiwei Ye, Jinshi Cui, Liwei Wang

Figure 1 for Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
Figure 2 for Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
Figure 3 for Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
Figure 4 for Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
* Accepted by NeurIPS 2021 (spotlight). Code is available at https://github.com/hzhupku/SemiSeg-AEL 
  Access Paper or Ask Questions

Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility


Oct 03, 2021
Li Chen, Yulin Ding, Han Hu, Qing Zhu, Haowei Zeng, Haojia Yu, Qisen Shang, Yongfei Song

Figure 1 for Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
Figure 2 for Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
Figure 3 for Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
Figure 4 for Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility

  Access Paper or Ask Questions

Video Swin Transformer


Jun 24, 2021
Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu

Figure 1 for Video Swin Transformer
Figure 2 for Video Swin Transformer
Figure 3 for Video Swin Transformer
Figure 4 for Video Swin Transformer

  Access Paper or Ask Questions

End-to-End Semi-Supervised Object Detection with Soft Teacher


Jun 17, 2021
Mengde Xu, Zheng Zhang, Han Hu, Jianfeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, Zicheng Liu

Figure 1 for End-to-End Semi-Supervised Object Detection with Soft Teacher
Figure 2 for End-to-End Semi-Supervised Object Detection with Soft Teacher
Figure 3 for End-to-End Semi-Supervised Object Detection with Soft Teacher
Figure 4 for End-to-End Semi-Supervised Object Detection with Soft Teacher

  Access Paper or Ask Questions

Aligning Pretraining for Detection via Object-Level Contrastive Learning


Jun 04, 2021
Fangyun Wei, Yue Gao, Zhirong Wu, Han Hu, Stephen Lin

Figure 1 for Aligning Pretraining for Detection via Object-Level Contrastive Learning
Figure 2 for Aligning Pretraining for Detection via Object-Level Contrastive Learning
Figure 3 for Aligning Pretraining for Detection via Object-Level Contrastive Learning
Figure 4 for Aligning Pretraining for Detection via Object-Level Contrastive Learning

  Access Paper or Ask Questions

TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system


May 28, 2021
Kaixin Zhang, Hongzhi Wang, Tongxin Li, Han Hu, Jiye Qiu, Songling Zou

Figure 1 for TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system
Figure 2 for TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system
Figure 3 for TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system
Figure 4 for TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system

  Access Paper or Ask Questions

Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning


May 12, 2021
Yansong Tang, Zhenyu Jiang, Zhenda Xie, Yue Cao, Zheng Zhang, Philip H. S. Torr, Han Hu

Figure 1 for Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
Figure 2 for Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
Figure 3 for Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
Figure 4 for Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
* Technical report 
  Access Paper or Ask Questions

Self-Supervised Learning with Swin Transformers


May 11, 2021
Zhenda Xie, Yutong Lin, Zhuliang Yao, Zheng Zhang, Qi Dai, Yue Cao, Han Hu

Figure 1 for Self-Supervised Learning with Swin Transformers
Figure 2 for Self-Supervised Learning with Swin Transformers
Figure 3 for Self-Supervised Learning with Swin Transformers
Figure 4 for Self-Supervised Learning with Swin Transformers

  Access Paper or Ask Questions

Group-Free 3D Object Detection via Transformers


Apr 23, 2021
Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong

Figure 1 for Group-Free 3D Object Detection via Transformers
Figure 2 for Group-Free 3D Object Detection via Transformers
Figure 3 for Group-Free 3D Object Detection via Transformers
Figure 4 for Group-Free 3D Object Detection via Transformers

  Access Paper or Ask Questions

Capsule Network is Not More Robust than Convolutional Network


Mar 29, 2021
Jindong Gu, Volker Tresp, Han Hu

Figure 1 for Capsule Network is Not More Robust than Convolutional Network
Figure 2 for Capsule Network is Not More Robust than Convolutional Network
Figure 3 for Capsule Network is Not More Robust than Convolutional Network
Figure 4 for Capsule Network is Not More Robust than Convolutional Network
* IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 
  Access Paper or Ask Questions

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows


Mar 25, 2021
Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo

Figure 1 for Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Figure 2 for Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Figure 3 for Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Figure 4 for Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
* The first 4 authors contribute equally 
  Access Paper or Ask Questions

Boosting Adversarial Transferability through Enhanced Momentum


Mar 19, 2021
Xiaosen Wang, Jiadong Lin, Han Hu, Jingdong Wang, Kun He

Figure 1 for Boosting Adversarial Transferability through Enhanced Momentum
Figure 2 for Boosting Adversarial Transferability through Enhanced Momentum
Figure 3 for Boosting Adversarial Transferability through Enhanced Momentum
Figure 4 for Boosting Adversarial Transferability through Enhanced Momentum
* 13 pages 
  Access Paper or Ask Questions

Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps


Feb 04, 2021
Yujin Huang, Han Hu, Chunyang Chen

Figure 1 for Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
Figure 2 for Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
Figure 3 for Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
Figure 4 for Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
* Accepted to the 43rd International Conference on Software Engineering, Software Engineering in Practice Track. This is a preprint version, the copyright belongs to The Institute of Electrical and Electronics Engineers 
  Access Paper or Ask Questions

Global Context Networks


Dec 24, 2020
Yue Cao, Jiarui Xu, Stephen Lin, Fangyun Wei, Han Hu

Figure 1 for Global Context Networks
Figure 2 for Global Context Networks
Figure 3 for Global Context Networks
Figure 4 for Global Context Networks
* To appear in TPAMI. Full version of GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond (arXiv:1904.11492) 
  Access Paper or Ask Questions

Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images


Nov 26, 2020
Qing Zhu, Shengzhi Huang, Han Hu, Haifeng Li, Min Chen, Ruofei Zhong

Figure 1 for Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images
Figure 2 for Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images
Figure 3 for Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images
Figure 4 for Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images

  Access Paper or Ask Questions

Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment


Nov 24, 2020
Qing Zhu, Qishen Shang, Han Hu, Haojia Yu, Ruofei Zhong

Figure 1 for Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment
Figure 2 for Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment
Figure 3 for Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment
Figure 4 for Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment

  Access Paper or Ask Questions

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning


Nov 19, 2020
Zhenda Xie, Yutong Lin, Zheng Zhang, Yue Cao, Stephen Lin, Han Hu

Figure 1 for Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
Figure 2 for Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
Figure 3 for Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
Figure 4 for Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

  Access Paper or Ask Questions

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder


Oct 29, 2020
Cheng Chi, Fangyun Wei, Han Hu

Figure 1 for RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Figure 2 for RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Figure 3 for RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Figure 4 for RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
* NeurIPS2020 Spotlight 
  Access Paper or Ask Questions