Alert button
Picture for Haokui Zhang

Haokui Zhang

Alert button

Bridging Sensor Gaps via Single-Direction Tuning for Hyperspectral Image Classification

Sep 22, 2023
Xizhe Xue, Haokui Zhang, Ying Li, Liuwei Wan, Zongwen Bai, Mike Zheng Shou

Figure 1 for Bridging Sensor Gaps via Single-Direction Tuning for Hyperspectral Image Classification
Figure 2 for Bridging Sensor Gaps via Single-Direction Tuning for Hyperspectral Image Classification
Figure 3 for Bridging Sensor Gaps via Single-Direction Tuning for Hyperspectral Image Classification
Figure 4 for Bridging Sensor Gaps via Single-Direction Tuning for Hyperspectral Image Classification
Viaarxiv icon

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

Jun 19, 2023
Yun Yi, Haokui Zhang, Rong Xiao, Nannan Wang, Xiaoyu Wang

Figure 1 for NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
Figure 2 for NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
Figure 3 for NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
Figure 4 for NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
Viaarxiv icon

Teacher Agent: A Non-Knowledge Distillation Method for Rehearsal-based Video Incremental Learning

Jun 01, 2023
Shengqin Jiang, Yaoyu Fang, Haokui Zhang, Peng Wang, Yuankai Qi, Qingshan Liu

Figure 1 for Teacher Agent: A Non-Knowledge Distillation Method for Rehearsal-based Video Incremental Learning
Figure 2 for Teacher Agent: A Non-Knowledge Distillation Method for Rehearsal-based Video Incremental Learning
Figure 3 for Teacher Agent: A Non-Knowledge Distillation Method for Rehearsal-based Video Incremental Learning
Figure 4 for Teacher Agent: A Non-Knowledge Distillation Method for Rehearsal-based Video Incremental Learning
Viaarxiv icon

NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction

Nov 15, 2022
Yun Yi, Haokui Zhang, Wenze Hu, Nannan Wang, Xiaoyu Wang

Figure 1 for NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction
Figure 2 for NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction
Figure 3 for NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction
Figure 4 for NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction
Viaarxiv icon

CabViT: Cross Attention among Blocks for Vision Transformer

Nov 14, 2022
Haokui Zhang, Wenze Hu, Xiaoyu Wang

Figure 1 for CabViT: Cross Attention among Blocks for Vision Transformer
Figure 2 for CabViT: Cross Attention among Blocks for Vision Transformer
Figure 3 for CabViT: Cross Attention among Blocks for Vision Transformer
Figure 4 for CabViT: Cross Attention among Blocks for Vision Transformer
Viaarxiv icon

ParCNetV2: Oversized Kernel with Enhanced Attention

Nov 14, 2022
Ruihan Xu, Haokui Zhang, Wenze Hu, Shiliang Zhang, Xiaoyu Wang

Figure 1 for ParCNetV2: Oversized Kernel with Enhanced Attention
Figure 2 for ParCNetV2: Oversized Kernel with Enhanced Attention
Figure 3 for ParCNetV2: Oversized Kernel with Enhanced Attention
Figure 4 for ParCNetV2: Oversized Kernel with Enhanced Attention
Viaarxiv icon

Fast-ParC: Position Aware Global Kernel for ConvNets and ViTs

Oct 08, 2022
Tao Yang, Haokui Zhang, Wenze Hu, Changwen Chen, Xiaoyu Wang

Figure 1 for Fast-ParC: Position Aware Global Kernel for ConvNets and ViTs
Figure 2 for Fast-ParC: Position Aware Global Kernel for ConvNets and ViTs
Figure 3 for Fast-ParC: Position Aware Global Kernel for ConvNets and ViTs
Figure 4 for Fast-ParC: Position Aware Global Kernel for ConvNets and ViTs
Viaarxiv icon

EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers

Mar 15, 2022
Haokui Zhang, Wenze Hu, Xiaoyu Wang

Figure 1 for EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers
Figure 2 for EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers
Figure 3 for EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers
Figure 4 for EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers
Viaarxiv icon

3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification

Oct 21, 2021
Xizhe Xue, Haokui Zhang, Zongwen Bai, Ying Li

Figure 1 for 3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification
Figure 2 for 3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification
Figure 3 for 3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification
Figure 4 for 3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification
Viaarxiv icon