Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition
Not on the map. Why?
Abstract (arXiv)
Weakly supervised image segmentation (WSSS) from image tags remains challenging due to its under-constraint nature. Most mainstream work focus on the extraction of class activation map (CAM) and imposing various additional regularization. Contrary to the mainstream, we propose to frame WSSS as a problem of reconstruction from decomposition of the image using its mask, under which most regularization are embedded implicitly within the framework of the new problem. Our approach has demonstrated promising results on initial experiments, and shown robustness against the problem of background ambiguity. Our code is available at urlhttps://github.com/xuanrui-work/WSSSByRec.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 9 references that are in the map. First posted on arXiv 2 Sep 2024.
Builds on
7 of 9 references.
References · 7
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2015Learning Deep Features for Discriminative Localizationcited by 2,436
- 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
- 2020Single-Stage Semantic Segmentation from Image Labelscited by 167
- 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
Built on by
Not cited yet.