Junwen Pan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junwen Pan has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Ming Lu
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing 100871, China
2 shared publications - Qi She
Bytedance AI Lab, China
2 shared publications - Shanghang Zhang
Peking University, Beijing, China
2 shared publications - Yuan Zhang
Peking University
2 shared publications - Chang Liu
ByteDance Inc., Beijing, China
1 shared publication - Chaoqi Chen
Shenzhen University
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6040-6048
Swap-JEPA: Learning Latent Correspondences for Zero-shot Object Swapping in Live Shopping
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6040-6048
Open AccessSwap-JEPA: Learning Latent Correspondences for Zero-shot Object Swapping in Live Shopping
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15041-15050
ZoomV: Temporal Zoom-in for Efficient Long Video Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15041-15050
Open AccessZoomV: Temporal Zoom-in for Efficient Long Video Understanding
- 1 October 2026
- Published by Springer Nature
- p. 227-244
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
- 1 October 2026
- Published by Springer Nature
- p. 227-244
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
- 6 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (2) , 507-518
GraphSKT: Graph-Guided Structured Knowledge Transfer for Domain Adaptive Lesion Detection
Adversarial-based adaptation has dominated the area of domain adaptive detection over the past few years. Despite their general efficacy for various tasks, the learned representations may not capture the intrinsic topological structures of the whole images and thus are vulnerable to distributional shifts especially in real-world applications, such as geometric distortions across imaging devices in medical images. In this case, forcefully matching data distributions across domains cannot ensure precise knowledge transfer and are prone to result in the negative transfer. In this paper, we explore the problem of domain adaptive lesion detection from the perspective of relational reasoning, and propose a Graph-Structured Knowledge Transfer (GraphSKT) framework to perform hierarchical reasoning by modeling both the intra- and inter-domain topological structures. To be specific, we utilize cross-domain correspondence to mine meaningful foreground regions for representing graph nodes and explicitly endow each node with contextual information. Then, the intra- and inter-domain graphs are built on the top of instance-level features to achieve a high-level understanding of the lesion and whole medical image, and transfer the structured knowledge from source to target domains. The contextual and semantic information is propagated through graph nodes methodically, enhancing the expressive power of learned features for the lesion detection tasks. Extensive experiments on two types of challenging datasets demonstrate that the proposed GraphSKT significantly outperforms the state-of-the-art approaches for detection of polyps in colonoscopy images and of mass in mammographic images.
- 6 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (2) , 507-518
GraphSKT: Graph-Guided Structured Knowledge Transfer for Domain Adaptive Lesion Detection
Adversarial-based adaptation has dominated the area of domain adaptive detection over the past few years. Despite their general efficacy for various tasks, the learned representations may not capture the intrinsic topological structures of the whole images and thus are vulnerable to distributional shifts especially in real-world applications, such as geometric distortions across imaging devices in medical images. In this case, forcefully matching data distributions across domains cannot ensure precise knowledge transfer and are prone to result in the negative transfer. In this paper, we explore the problem of domain adaptive lesion detection from the perspective of relational reasoning, and propose a Graph-Structured Knowledge Transfer (GraphSKT) framework to perform hierarchical reasoning by modeling both the intra- and inter-domain topological structures. To be specific, we utilize cross-domain correspondence to mine meaningful foreground regions for representing graph nodes and explicitly endow each node with contextual information. Then, the intra- and inter-domain graphs are built on the top of instance-level features to achieve a high-level understanding of the lesion and whole medical image, and transfer the structured knowledge from source to target domains. The contextual and semantic information is propagated through graph nodes methodically, enhancing the expressive power of learned features for the lesion detection tasks. Extensive experiments on two types of challenging datasets demonstrate that the proposed GraphSKT significantly outperforms the state-of-the-art approaches for detection of polyps in colonoscopy images and of mass in mammographic images.
- Open Access
Label-efficient Hybrid-supervised Learning for Medical Image Segmentation
Due to the lack of expertise for medical image annotation, the investigation of label-efficient methodology for medical image segmentation becomes a heated topic. Recent progresses focus on the efficient utilization of weak annotations together with few strongly-annotated labels so as to achieve comparable segmentation performance in many unprofessional scenarios. However, these approaches only concentrate on the supervision inconsistency between strongly- and weakly-annotated instances but ignore the instance inconsistency inside the weakly-annotated instances, which inevitably leads to performance degradation. To address this problem, we propose a novel label-efficient hybrid-supervised framework, which considers each weakly-annotated instance individually and learns its weight guided by the gradient direction of the strongly-annotated instances, so that the high-quality prior in the strongly-annotated instances is better exploited and the weakly-annotated instances are depicted more precisely. Specially, our designed dynamic instance indicator (DII) realizes the above objectives, and is adapted to our dynamic co-regularization (DCR) framework further to alleviate the erroneous accumulation from distortions of weak annotations. Extensive experiments on two hybrid-supervised medical segmentation datasets demonstrate that with only 10% strong labels, the proposed framework can leverage the weak labels efficiently and achieve competitive performance against the 100% strong-label supervised scenario.
Open AccessLabel-efficient Hybrid-supervised Learning for Medical Image Segmentation
Due to the lack of expertise for medical image annotation, the investigation of label-efficient methodology for medical image segmentation becomes a heated topic. Recent progresses focus on the efficient utilization of weak annotations together with few strongly-annotated labels so as to achieve comparable segmentation performance in many unprofessional scenarios. However, these approaches only concentrate on the supervision inconsistency between strongly- and weakly-annotated instances but ignore the instance inconsistency inside the weakly-annotated instances, which inevitably leads to performance degradation. To address this problem, we propose a novel label-efficient hybrid-supervised framework, which considers each weakly-annotated instance individually and learns its weight guided by the gradient direction of the strongly-annotated instances, so that the high-quality prior in the strongly-annotated instances is better exploited and the weakly-annotated instances are depicted more precisely. Specially, our designed dynamic instance indicator (DII) realizes the above objectives, and is adapted to our dynamic co-regularization (DCR) framework further to alleviate the erroneous accumulation from distortions of weak annotations. Extensive experiments on two hybrid-supervised medical segmentation datasets demonstrate that with only 10% strong labels, the proposed framework can leverage the weak labels efficiently and achieve competitive performance against the 100% strong-label supervised scenario.