Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation
This addresses the challenge of open-vocabulary camouflaged object segmentation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of segmenting camouflaged objects of arbitrary unseen categories by proposing a classifier-centric adaptive framework, which improves segmentation metrics such as increasing cIoU from 0.443 to 0.493 and cSm from 0.579 to 0.658 on the OVCamo benchmark.
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.