Picture for Xiaodan Liang

Xiaodan Liang

Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

Apr 12, 2022
Minbin Huang, Zhijian Huang, Changlin Li, Xin Chen, Hang Xu, Zhenguo Li, Xiaodan Liang

Figure 1 for Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

Figure 2 for Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

Figure 3 for Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

Figure 4 for Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

* Accepted by CVPR 2022

Access Paper or Ask Questions

Beyond Fixation: Dynamic Window Visual Transformer

Apr 08, 2022
Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, Xiaojun Chang

Figure 1 for Beyond Fixation: Dynamic Window Visual Transformer

Figure 2 for Beyond Fixation: Dynamic Window Visual Transformer

Figure 3 for Beyond Fixation: Dynamic Window Visual Transformer

Figure 4 for Beyond Fixation: Dynamic Window Visual Transformer

* CVPR2022

Access Paper or Ask Questions

Dressing in the Wild by Watching Dance Videos

Mar 29, 2022
Xin Dong, Fuwei Zhao, Zhenyu Xie, Xijin Zhang, Daniel K. Du, Min Zheng, Xiang Long, Xiaodan Liang, Jianchao Yang

Figure 1 for Dressing in the Wild by Watching Dance Videos

Figure 2 for Dressing in the Wild by Watching Dance Videos

Figure 3 for Dressing in the Wild by Watching Dance Videos

Figure 4 for Dressing in the Wild by Watching Dance Videos

* Accepted at CVPR2022, Project: https://awesome-wflow.github.io

Access Paper or Ask Questions

Automated Progressive Learning for Efficient Training of Vision Transformers

Mar 28, 2022
Changlin Li, Bohan Zhuang, Guangrun Wang, Xiaodan Liang, Xiaojun Chang, Yi Yang

Figure 1 for Automated Progressive Learning for Efficient Training of Vision Transformers

Figure 2 for Automated Progressive Learning for Efficient Training of Vision Transformers

Figure 3 for Automated Progressive Learning for Efficient Training of Vision Transformers

Figure 4 for Automated Progressive Learning for Efficient Training of Vision Transformers

* Accepted to CVPR 2022

Access Paper or Ask Questions

Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

Mar 08, 2022
Xiwen Liang, Fengda Zhu, Lingling Li, Hang Xu, Xiaodan Liang

Figure 1 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

Figure 2 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

Figure 3 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

Figure 4 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

* Accepted by ACL 2022

Access Paper or Ask Questions