I am a fourth-year Ph.D. student at Beijing Institute of Technology, advised by Prof. Shuang Li and Prof. Chi Harold Liu. I received my Bachelor's degree in Software Engineering from BIT (2015-2019).
My research interests are in foundation models, transfer learning, and data-efficient learning.
Contact: I'm always happy to discuss or collaborate! Feel free to drop me an email if you're interested.
News
-
[Feb 2023] Two co-authored papers ( EVA, RoTTA) are accepted by CVPR 2023!
-
[Jan 2023] One first-authored SePiCo for domain adaptive semantic segmentation is accepted by T-PAMI (IF: 24.31)!
-
[Nov 2022] One co-authored ORAL paper for semantic segmentation in adverse conditions is accepted by AAAI 2023!
-
[Nov 2022] EVA Unit-01 Launched!
-
[Jun 2022] One first-authored paper is accepted by TKDE!
-
[Mar 2022] One first-authored ORAL paper for data-efficient semantic segmentation is accepted by CVPR 2022!
-
[Dec 2021] One first-authored paper for active domain adaptation is accepted by AAAI 2022!
-
[Feb 2021] One co-authored paper for domain adaptation is accepted by T-PAMI (IF: 24.31)!
Read More
-
[Apr 2022] One co-authored paper for partial domain adaptation is accepted by T-CYB!
-
[Dec 2020] One co-authored paper for bi-classifier domain adaptation is accepted by AAAI 2021!
-
[Jul 2020] One co-authored paper for heterogeneous domain adaptation is accepted by ACM MM 2020!
-
[Dec 2019] One co-authored paper for domain adaptation is accepted by AAAI 2020!
-
[Jul 2019] My starting research journey is accepted by ACM MM 2019!
Read Less
Recent Publications & Technical Reports
|
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic SegmentationBinhui 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 |
|
EVA: Exploring the Limits of Masked Visual Representation Learning at ScaleYuxin 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 |
|
VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse ConditionsMingjia 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 |
|
Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic SegmentationBinhui 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 ApproachBinhui 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 |
|
Generalized Domain Conditioned Adaptation NetworkShuang 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 |
|
A Collaborative Alignment Framework of Transferable Knowledge Extraction for Unsupervised Domain AdaptationBinhui 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 |
|
Simultaneous Semantic Alignment Network for Heterogeneous Domain AdaptationShuang 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 |
|
Joint Adversarial Domain AdaptationShuang Li, Chi Harold Liu, Binhui Xie, Limin Su, Zhengming Ding, and Gao Huang JADA simultaneously aligns domain-wise and class-wise distributions across source and target in a unified adversarial learning process. Paper Code Poster |
Invited Talks
-
2022.6, Synced (online), Towards Fewer Annotations: Active Learning for Adaptive Semantic Segmentation.
-
2022.6, ReadPaper (online), Towards Fewer Annotations: Active Learning for Adaptive Semantic Segmentation.
-
2022.5, Zhidx Course (onine), Active Learning under Distribution Shift.
-
2022.3, AI Drive (online), Energy-based Active Domain Adaptation.
-
2021.10, VALSE (Hangzhou), Generalized Domain Conditioned Adaptation Network.
Academic Service
Organizer of Workshop: VALSE 2022 (Student Workshop).
Reviewer for ICCV'23, CVPR'23, ICLR'23, AAAI'23, ECCV'22, CVPR'22, AAAI'22, ICCV'21, CVPR'21, AAAI'21, etc.
Reviewer for TPAMI, TNNLS, TMM, etc.
Selected Honors and Awards
-
Excellent Undergraduate in Beijing Institute of Technology, 2019.
Contact
-
Email: binhuixie@bit.edu.cn
-
Address: Room 1106, Central Teaching Building, Beijing Institute of Technology, Beijing