Saved in:
Bibliographic Details
Main Author: Zeng, Xuanrui
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.01472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929483648335872
author Zeng, Xuanrui
author_facet Zeng, Xuanrui
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2409_01472
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition
Zeng, Xuanrui
Computer Vision and Pattern Recognition
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}.
title Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.01472