Binhui Xie

Binhui Xie is a fifth year Ph.D. student in the School of Computer Science and Technology at Beijing Institute of Technology, advised by Prof. Shuang Li and Prof. Chi Liu. Before that, he received his B.E. degree in Software Engineering at BIT in 2019.

My research interests are in transfer learning, data-efficient learning, and multimodal learning.

Contact: I'm always happy to discuss or collaborate! Feel free to seed me an email(binhuixie@bit.edu.cn; minexbh@gmail.com) if you're interested.

I’m on job market (2025)! If you are interested in me, contact me via Email. (Download my resumé)



News


  • [Sep 2024] Our W-Diff on domain-incremental training is accepted by NeurIPS 2024, congrats!

  • [May 2024] Our PaRe on cross-modal fine-tuning is accepted by ICML 2024, congrats! [pdf] [code]

  • [Nov 2023] Both SePiCo and CAF are selected as Highly Cited Paper!! [screenshot1] [screenshot2]

  • [Sep 2023] EVA is selected as the 7th most influential paper in CVPR 2023! [list]

  • [Sep 2023] Annotator for label-efficient LiDAR segmentation is accepted by NeurIPS 2023! [pdf] [code]

  • [Feb 2023] Our EVA (Highlight) on vision foundation models and RoTTA on test-time adaptation are accepted by CVPR 2023, congrats!

  • [Jan 2023] Our work on cross-domain semantic segmentation (SePiCo) is accepted by T-PAMI (IF: 23.6)! [pdf] [code]

  • [Nov 2022] Our study on adverse-condition semantic segmentation (VBLC) is accepted by AAAI 2023 as Oral, congrats! [pdf] [code]

  • [Nov 2022] EVA-01 Launched! [pdf] [code]

  • [Jun 2022] CAF is accepted by TKDE! [pdf] [code]

  • [Mar 2022] Our work on data-efficient semantic segmentation (RIPU) is accepted by CVPR 2022 as Oral! [pdf] [code]

  • [Dec 2021] Our work on active domain adaptation (EADA) is accepted by AAAI 2022! [pdf] [code]

  • [Feb 2021] The extension of DCAN got accepted by T-PAMI (IF: 23.6), congrats! [pdf] [code]

  • [Jul 2020] Our work on heterogeneous domain adaptation (SSAN) is accepted by ACM MM 2020! [pdf] [code]

  • [Jul 2019] My starting research journey on domain adaptation (JADA) is accepted by ACM MM 2019! [pdf] [code]


Selected Publications


EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

IEEE Conference on Computer Vision and Pattern Recognition (CVPR Highlights), 2023

PaperDigest Most Influential Papers

Yuxin Fang, Wen Wang, Binhui Xie, Quan Sun, Ledell Yu Wu, Xinggang Wang, Tiejun Huang, Xinlong Wang, and Yue Cao

EVA is the first open-sourced billion-scale vision foundation model that achieves state-of-the-art performance on a broad range of downstream tasks.

Paper Code
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF: 23.6), 2023

ESI Highly Cited Paper

Binhui Xie, Shuang Li, Mingjia Li, Chi Harold Liu, Gao Huang, and Guoren Wang

A novel one-stage adaptation framework that highlights the semantic concepts of individual pixel to promote learning of class-discriminative and class-balanced pixel embedding space across domains.

Project Page Paper Code
Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation

Advances in Neural Information Processing Systems (NeurIPS), 2023

Binhui Xie, Shuang Li, Qingju Guo, Chi Harold Liu, and Xinjing Cheng

We established a simple and general baseline for label-efficient LiDAR semantic segmentation.

Project Page Paper Code Video Slides Poster
Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR Oral), 2022

Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, and Xinjing Cheng

A region-based acquisition strategy for DA Segmentation queries image regions that are both diverse in spatial adjacency and uncertain in prediction output.

Paper Code Video Slides Poster
Active Learning for Domain Adaptation: An Energy-based Approach

AAAI Conference on Artificial Intelligence (AAAI), 2022

Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, Xinjing Cheng, and Guoren Wang

A new perspective to select a highly informative subset of unlabeled target data under domain shift via exploiting free energy biases across domains.

Paper Code Video Slides Poster
A Collaborative Alignment Framework of Transferable Knowledge Extraction for Unsupervised Domain Adaptation

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023

ESI Highly Cited Paper

Binhui Xie, Shuang Li, Fangrui Lv, Chi Harold Liu, Guoren Wang, and Dapeng Wu

We introduce a collaborative alignment framework that integrates global structure information and local semantic consistency into a unified deep model.

Paper Code
Generalized Domain Conditioned Adaptation Network

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF: 23.6), 2022

Shuang Li, Binhui Xie, Qiuxia Lin, Chi Harold Liu, Gao Huang, and Guoren Wang

We develop GDCAN to automatically determine whether domain channel activations should be separately modeled in each attention module for domain adaptaion problem.

Paper Code Poster
Robust Test-Time Adaptation in Dynamic Scenarios

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Longhui Yuan, Binhui Xie and Shuang Li

RoTTA presents a new practical test-time adaptation setting where environments gradually change and the test data is sampled correlatively over time.

Paper Code Video
VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

AAAI Conference on Artificial Intelligence (AAAI Oral), 2023

Mingjia Li*, Binhui Xie*, Shuang Li, Chi Harold Liu, and Xinjing Cheng

VBLC tackles the problem of domain adaptive semantic segmentation under adverse conditions, getting rid of reference images.

Project Page Paper Code Video Poster
Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation

ACM International Conference on Multimedia (ACM MM), 2020

Shuang Li, Binhui Xie, Jiashu Wu, Ying Zhao, Chi Harold Liu, and Zhengming Ding

A HDA method simultaneously exploits correlations among categories and aligns the centroids for each category across domains.

Paper Code Slides Poster

Invited Talks


  • 2023.11, AI TIME (online), A Generic Active Learning Baseline in LiDAR Semantic Segmentation.

  • 2023.4, VALSE_Webinar (recorded), Towards Fewer Annotations: Active Learning for Adaptive Semantic Segmentation.

  • 2022.6, Synced (online), Towards Fewer Annotations for Adaptive Semantic Segmentation.

  • 2022.6, ReadPaper (online), Active Learning for Adaptive Semantic Segmentation.

  • 2022.5, Zhidx Course (onine), Domain Adaptation meets Active Learning.

  • 2022.3, AI Drive (online), Energy-based Active Domain Adaptation.

  • 2021.10, VALSE (Hangzhou), spotlight & poster, Generalized Domain Conditioned Adaptation.


Academic Service

  • Conference Reviewer: ICML24, ICLR25/24/23, NeurIPS24/23 (Top Reviewers@2023), CVPR24/23/22/21, ICCV23/21, ECCV24/22

  • Journal Reviewer: IJCV, T-IP, T-KDE, T-CSVT, Pattern Recognition, T-IV

  • Organizer of Workshop: VALSE 2022 (Student Workshop).


Teaching Assistant


Machine Learning Essentials, Spring 2021 & Spring 2022, Instructor: Prof. Li


Selected Honors and Awards

  • "Xu Teli" Scholarship(徐特立奖学金,北理工最高荣誉奖学金), Beijing Institute of Technology, 2024.

  • "Xu Teli" Scholarship(徐特立奖学金,北理工最高荣誉奖学金), Beijing Institute of Technology, 2024.

  • Excellent Doctoral Dissertation Fund(优秀博士学位论文育苗基金), Beijing Institute of Technology, 2024.

  • Top Reviewers and Scholar Award, NeurIPS 2023.

  • Young Scientist Group (青源会), BAAI, 2023.

  • National Scholarship (国家奖学金), Ministry of Education of China, 2023.

  • 3rd place, VisDA-2022@NeurIPS, 2022.

  • Special Academic Scholarship (特等学业奖学金), Beijing Institute of Technology, 2022/2023.

  • CETC GUORUI Scholarship (国瑞奖学金), 2021.

  • Excellent Undergraduate & Graduation Thesis at Beijing Institute of Technology, 2019.


Contact


  • Email: binhuixie@bit.edu.cn

  • Address: Room 1106, Central Teaching Building, Beijing Institute of Technology, Beijing