# Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition

Source: [Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition](<https://www.sota2.com/research/paper/68fa74b21e209131cea63554>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:16:29.756Z

Authors: Xuanrui Zeng

Published: 2024-09-02T21:36:59.000Z

## Abstract

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 \\url{https://github.com/xuanrui-work/WSSSByRec}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.01472>)

[PDF](<https://arxiv.org/pdf/2409.01472.pdf>)