Alert button
Picture for Shumin Han

Shumin Han

Alert button

Heterogeneous Generative Knowledge Distillation with Masked Image Modeling

Sep 18, 2023
Ziming Wang, Shumin Han, Xiaodi Wang, Jing Hao, Xianbin Cao, Baochang Zhang

Figure 1 for Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
Figure 2 for Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
Figure 3 for Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
Figure 4 for Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
Viaarxiv icon

Simple parameter-free self-attention approximation

Jul 22, 2023
Yuwen Zhai, Jing Hao, Liang Gao, Xinyu Li, Yiping Gao, Shumin Han

Figure 1 for Simple parameter-free self-attention approximation
Figure 2 for Simple parameter-free self-attention approximation
Figure 3 for Simple parameter-free self-attention approximation
Figure 4 for Simple parameter-free self-attention approximation
Viaarxiv icon

Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models

May 08, 2023
Wenkai Dong, Song Xue, Xiaoyue Duan, Shumin Han

Figure 1 for Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models
Figure 2 for Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models
Figure 3 for Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models
Figure 4 for Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models
Viaarxiv icon

Language-aware Multiple Datasets Detection Pretraining for DETRs

Apr 07, 2023
Jing Hao, Song Chen, Xiaodi Wang, Shumin Han

Figure 1 for Language-aware Multiple Datasets Detection Pretraining for DETRs
Figure 2 for Language-aware Multiple Datasets Detection Pretraining for DETRs
Figure 3 for Language-aware Multiple Datasets Detection Pretraining for DETRs
Figure 4 for Language-aware Multiple Datasets Detection Pretraining for DETRs
Viaarxiv icon

Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning

Nov 28, 2022
Xiaoyue Duan, Guoliang Kang, Runqi Wang, Shumin Han, Song Xue, Tian Wang, Baochang Zhang

Figure 1 for Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Figure 2 for Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Figure 3 for Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Figure 4 for Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Viaarxiv icon

CAE v2: Context Autoencoder with CLIP Target

Nov 17, 2022
Xinyu Zhang, Jiahui Chen, Junkun Yuan, Qiang Chen, Jian Wang, Xiaodi Wang, Shumin Han, Xiaokang Chen, Jimin Pi, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

Figure 1 for CAE v2: Context Autoencoder with CLIP Target
Figure 2 for CAE v2: Context Autoencoder with CLIP Target
Figure 3 for CAE v2: Context Autoencoder with CLIP Target
Figure 4 for CAE v2: Context Autoencoder with CLIP Target
Viaarxiv icon

Context Autoencoder for Self-Supervised Representation Learning

Feb 07, 2022
Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, Jingdong Wang

Figure 1 for Context Autoencoder for Self-Supervised Representation Learning
Figure 2 for Context Autoencoder for Self-Supervised Representation Learning
Figure 3 for Context Autoencoder for Self-Supervised Representation Learning
Figure 4 for Context Autoencoder for Self-Supervised Representation Learning
Viaarxiv icon

Oriented Object Detection with Transformer

Jun 06, 2021
Teli Ma, Mingyuan Mao, Honghui Zheng, Peng Gao, Xiaodi Wang, Shumin Han, Errui Ding, Baochang Zhang, David Doermann

Figure 1 for Oriented Object Detection with Transformer
Figure 2 for Oriented Object Detection with Transformer
Figure 3 for Oriented Object Detection with Transformer
Figure 4 for Oriented Object Detection with Transformer
Viaarxiv icon

Dual-stream Network for Visual Recognition

May 31, 2021
Mingyuan Mao, Renrui Zhang, Honghui Zheng, Peng Gao, Teli Ma, Yan Peng, Errui Ding, Shumin Han

Figure 1 for Dual-stream Network for Visual Recognition
Figure 2 for Dual-stream Network for Visual Recognition
Figure 3 for Dual-stream Network for Visual Recognition
Figure 4 for Dual-stream Network for Visual Recognition
Viaarxiv icon

Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

May 07, 2021
Mingyuan Mao, Baochang Zhang, David Doermann, Jie Guo, Shumin Han, Yuan Feng, Xiaodi Wang, Errui Ding

Figure 1 for Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
Figure 2 for Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
Figure 3 for Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
Figure 4 for Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
Viaarxiv icon