English

USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation

Computer Vision and Pattern Recognition 2023-09-01 v2

Abstract

Seed area generation is usually the starting point of weakly supervised semantic segmentation (WSSS). Computing the Class Activation Map (CAM) from a multi-label classification network is the de facto paradigm for seed area generation, but CAMs generated from Convolutional Neural Networks (CNNs) and Transformers are prone to be under- and over-activated, respectively, which makes the strategies to refine CAMs for CNNs usually inappropriate for Transformers, and vice versa. In this paper, we propose a Unified optimization paradigm for Seed Area GEneration (USAGE) for both types of networks, in which the objective function to be optimized consists of two terms: One is a generation loss, which controls the shape of seed areas by a temperature parameter following a deterministic principle for different types of networks; The other is a regularization loss, which ensures the consistency between the seed areas that are generated by self-adaptive network adjustment from different views, to overturn false activation in seed areas. Experimental results show that USAGE consistently improves seed area generation for both CNNs and Transformers by large margins, e.g., outperforming state-of-the-art methods by a mIoU of 4.1% on PASCAL VOC. Moreover, based on the USAGE-generated seed areas on Transformers, we achieve state-of-the-art WSSS results on both PASCAL VOC and MS COCO.

Keywords

Cite

@article{arxiv.2303.07806,
  title  = {USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation},
  author = {Zelin Peng and Guanchun Wang and Lingxi Xie and Dongsheng Jiang and Wei Shen and Qi Tian},
  journal= {arXiv preprint arXiv:2303.07806},
  year   = {2023}
}

Comments

ICCV 2023 camera-ready version

R2 v1 2026-06-28T09:16:04.964Z