Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation
Year: 2023
Type: preprint
Abstract: Weakly supervised semantic segmentation with weak labels is a long-lived ill-posed problem. Mainstream methods mainly focus on improving the quality of pseudo labels. In this report, we attempt to explore the potential of 'prompt to masks' from the powerful class-agnostic large segmentation model, segment-anything. Specifically, different weak labels are used as prompts to the segment-anything model, generating precise class masks. The class masks are utilized to generate pseudo labels to train the segmentation networks. We have conducted extensive experiments on PASCAL VOC 2012 dataset. Experiments demonstrate that segment-anything can serve as a good pseudo-label generator. The code will be made publicly available.
Source: arXiv (Cornell University)
Authors: Jiang, Peng-Tao, Yang, Yuqi
Institutions: Zhejiang University, Nankai University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4368355574