Kai Han

Best Publications

• GhostNet: More Features From Cheap Operations

  Kai Han;Yunhe Wang;Qi Tian;Jianyuan Guo

  4116
  Citations

• Transformer in Transformer

  Unknown

  1049
  Citations

• Transformer in Transformer

  Unknown

  1030
  Citations

• CMT: Convolutional Neural Networks Meet Vision Transformers

  Unknown

  801
  Citations

• GhostNetV2: Enhance Cheap Operation with Long-Range Attention

  Unknown

  279
  Citations

• Distilling Object Detectors via Decoupled Features

  Jianyuan Guo;Kai Han;Yunhe Wang;Han Wu

  262
  Citations

• Patch Slimming for Efficient Vision Transformers

  Unknown

  255
  Citations

• Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

  Unknown

  249
  Citations

• A Survey on Visual Transformer

  Kai Han;Yunhe Wang;Hanting Chen;Xinghao Chen

  247
  Citations

• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

  Unknown

  209
  Citations

• An Image Patch is a Wave: Phase-Aware Vision MLP

  Unknown

  202
  Citations

• Autoencoder Inspired Unsupervised Feature Selection

  Unknown

  164
  Citations

• GhostNets on Heterogeneous Devices via Cheap Operations

  Unknown

  164
  Citations

• Hire-MLP: Vision MLP via Hierarchical Rearrangement

  Unknown

  149
  Citations

• Attribute-Aware Attention Model for Fine-grained Representation Learning

  Unknown

  142
  Citations

• Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN

  Shupeng Su;Chao Zhang;Kai Han;Yonghong Tian

  119
  Citations

• Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

  Jianyuan Guo;Kai Han;Yunhe Wang;Chao Zhang

  114
  Citations

• Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation

  Unknown

  113
  Citations

• GhostNet: More Features from Cheap Operations

  Kai Han;Yunhe Wang;Qi Tian;Jianyuan Guo

  108
  Citations

• A Survey on Vision Transformer

  Kai Han;Yunhe Wang;Hanting Chen;Xinghao Chen

  101
  Citations