GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model

This paper tackles a novel problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled data.

Data and Resources

Cite this as

Weiming Zhang, Yexin Liu, Xu Zheng, Lin Wang (2024). Dataset: GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model. https://doi.org/10.57702/cyr7lydz

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2403.16370
Author Weiming Zhang
More Authors
Yexin Liu
Xu Zheng
Lin Wang
Homepage https://vlislab22.github.io/GoodSAM/