Jie Qin
Papers
1
Total Citations
4
H-Index
1
About
Jie Qin is an emerging researcher working at the intersection of computer vision and weakly supervised learning, with a particular focus on segmentation tasks leveraging foundation models. Their most notable work, "WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models" (2024), represents a timely contribution to the field, exploring how large-scale foundation models — such as the Segment Anything Model (SAM) — can be adapted for fine-grained part segmentation under weak supervision constraints. This research addresses a critical challenge in computer vision: reducing the reliance on costly, pixel-level annotations while still achieving meaningful segmentation of object parts. By bridging weakly supervised learning paradigms with the representational power of modern foundation models, Qin's work opens new avenues for scalable and annotation-efficient vision systems. Although early in its citation trajectory with 4 citations since publication, the research touches on one of the most actively pursued directions in the community — adapting general-purpose vision foundation models to specialized downstream tasks. Qin's contributions position them as a researcher to watch as the field continues to mature around foundation model adaptation and efficient learning strategies.
Research Focus
Key Achievements
Top Papers
- 1