English

Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary

Computer Vision and Pattern Recognition 2022-10-18 v2

Abstract

Weakly-supervised semantic segmentation (WSSS) with image-level labels has been widely studied to relieve the annotation burden of the traditional segmentation task. In this paper, we show that existing fully-annotated base categories can help segment objects of novel categories with only image-level labels, even if base categories and novel categories have no overlap. We refer to this task as weak-shot semantic segmentation, which could also be treated as WSSS with auxiliary fully-annotated categories. Recent advanced WSSS methods usually obtain class activation maps (CAMs) and refine them by affinity propagation. Based on the observation that semantic affinity and boundary are class-agnostic, we propose a method under the WSSS framework to transfer semantic affinity and boundary from base to novel categories. As a result, we find that pixel-level annotation of base categories can facilitate affinity learning and propagation, leading to higher-quality CAMs of novel categories. Extensive experiments on PASCAL VOC 2012 dataset prove that our method significantly outperforms WSSS baselines on novel categories.

Keywords

Cite

@article{arxiv.2110.01519,
  title  = {Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary},
  author = {Siyuan Zhou and Li Niu and Jianlou Si and Chen Qian and Liqing Zhang},
  journal= {arXiv preprint arXiv:2110.01519},
  year   = {2022}
}

Comments

29 pages, 8 figures

R2 v1 2026-06-24T06:36:37.996Z