About
I am currently a postdoctoral researcher at Tongji University, jointly supervised by Prof. Guang Chen and Prof. Changjun Jiang. I earned my Ph.D. from Tongji University in 2024.
My research focuses on transfer learning and its applications in Embodied AI and AI4Science. I am particularly interested in developing robust and efficient algorithms for transfer learning and their applications in computer vision, robotics, and drug discovery.
Recent News
Selected Publications
* indicates equal contribution
RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions
We introduce RCP-Bench, the first comprehensive benchmark designed to evaluate the robustness of collaborative detection models under a wide range of real-world corruptions. RCPBench includes three new datasets (i.e., OPV2V-C, V2XSet-C, and DAIR-V2X-C) that simulate six collaborative cases and 14 types of camera corruption resulting from external environmental factors, sensor failures, and temporal misalignments.
General Class-Balanced Multicentric Dynamic Prototype Pseudo-Labeling for Source-Free Domain Adaptation
We promote the vanilla BMD to BMD-v2 by incorporating a consistency-guided reweighting strategy to improve inter-class balanced sampling, and leveraging the silhouettes metric to realize adaptive intra-class multicentric clustering.
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
Despite the simple global and local clustering (GLC) technique achieving commendable performance in separating "known" and "unknown" data, its reliance on pseudo-labeling supervision limits its capacity to discriminate among different "unknown" categories. To alleviate this, we promote GLC to GLC++ by developing a new contrastive affinity learning strategy.
HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation
In this paper, we delve into TTA in 3D point cloud segmentation and propose a novel Hierarchical Geometry Learning (HGL) framework. HGL comprises three complementary modules from local, global to temporal learning in a bottom-up manner.
LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
For Universal Domain Adaptation (UniDA), in this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data.
MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection
In this paper, we target a practical setting in IP protection, i.e., Source-free Model IP protection. To achieve this, we propose a novel MAsk Pruning (MAP) framework.
Upcycling Models under Domain and Category Shift
In this paper, we explore the Source-free Universal Domain Adaptation (SF-UniDA). SF-UniDA is appealing in view that universal model adaptation can be resolved only on the basis of a standard pre-trained closed-set model.
Modality-Agnostic Debiasing for Single Domain Generalization
Existing single-DG techniques commonly devise various data-augmentation algorithms. In contrast, we target a versatile Modality-Agnostic Debiasing (MAD) framework for single-DG, that enables generalization for different modalities.
Neuromorphic Vision-based Fall Localization in Event Streams with Temporal–spatial Attention Weighted Network
In this paper, we proposed a bio-inspired event-camera based falls temporal localization framework. Specifically, we propose a event density-based action proposal generation scheme, and introduce a temporal-spatial attention mechanism for action modeling.
ACM-Net: Action Context Modeling Network for Weakly-supervised Temporal Action Localization
In this paper, we propose an action-context modeling network termed ACM-Net, which integrates a three-branch attention module to measure the likelihood of each temporal point being action instance, context, or non-action background, simultaneously.
Education & Experience
Tongji University
Tongji University
Tongji University
Honors & Awards
Academic Services
Journal Reviewer
IEEE TPAMI, IJCV, IEEE TIP, IEEE TMM, IEEE TCSVT, ACM TOMM, etc.
Conference Reviewer
CVPR, ICCV, ECCV, ICRA, IROS, NeurIPS, etc.