Saved in:
Bibliographic Details
Main Authors: Zhang, Hanyu, Zhou, Yiming, Zhang, Jinxia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.24681
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911183723823104
author Zhang, Hanyu
Zhou, Yiming
Zhang, Jinxia
author_facet Zhang, Hanyu
Zhou, Yiming
Zhang, Jinxia
contents Open-vocabulary camouflaged object segmentation requires models to segment camouflaged objects of arbitrary categories unseen during training, placing extremely high demands on generalization capabilities. Through analysis of existing methods, it is observed that the classification component significantly affects overall segmentation performance. Accordingly, a classifier-centric adaptive framework is proposed to enhance segmentation performance by improving the classification component via a lightweight text adapter with a novel layered asymmetric initialization. Through the classification enhancement, the proposed method achieves substantial improvements in segmentation metrics compared to the OVCoser baseline on the OVCamo benchmark: cIoU increases from 0.443 to 0.493, cSm from 0.579 to 0.658, and cMAE reduces from 0.336 to 0.239. These results demonstrate that targeted classification enhancement provides an effective approach for advancing camouflaged object segmentation performance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24681
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation
Zhang, Hanyu
Zhou, Yiming
Zhang, Jinxia
Computer Vision and Pattern Recognition
Open-vocabulary camouflaged object segmentation requires models to segment camouflaged objects of arbitrary categories unseen during training, placing extremely high demands on generalization capabilities. Through analysis of existing methods, it is observed that the classification component significantly affects overall segmentation performance. Accordingly, a classifier-centric adaptive framework is proposed to enhance segmentation performance by improving the classification component via a lightweight text adapter with a novel layered asymmetric initialization. Through the classification enhancement, the proposed method achieves substantial improvements in segmentation metrics compared to the OVCoser baseline on the OVCamo benchmark: cIoU increases from 0.443 to 0.493, cSm from 0.579 to 0.658, and cMAE reduces from 0.336 to 0.239. These results demonstrate that targeted classification enhancement provides an effective approach for advancing camouflaged object segmentation performance.
title Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.24681