Saved in:
Bibliographic Details
Main Authors: Wang, Ye, Huang, Kai, Shen, Sumin, Ma, Chenyang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10894
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910123081859072
author Wang, Ye
Huang, Kai
Shen, Sumin
Ma, Chenyang
author_facet Wang, Ye
Huang, Kai
Shen, Sumin
Ma, Chenyang
contents Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic alignment, explicit uncertainty modeling, and robust boundary preservation. To address these issues, we propose EviRCOD, an integrated framework consisting of three core components: (1) a Reference-Guided Deformable Encoder (RGDE) that employs hierarchical reference-driven modulation and multi-scale deformable aggregation to inject semantic priors and align cross-scale representations; (2) an Uncertainty-Aware Evidential Decoder (UAED) that incorporates Dirichlet evidence estimation into hierarchical decoding to model uncertainty and propagate confidence across scales; and (3) a Boundary-Aware Refinement Module (BARM) that selectively enhances ambiguous boundaries by exploiting low-level edge cues and prediction confidence. Experiments on the Ref-COD benchmark demonstrate that EviRCOD achieves state-of-the-art detection performance while providing well-calibrated uncertainty estimates. Code is available at: https://github.com/blueecoffee/EviRCOD.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10894
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
Wang, Ye
Huang, Kai
Shen, Sumin
Ma, Chenyang
Computer Vision and Pattern Recognition
Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic alignment, explicit uncertainty modeling, and robust boundary preservation. To address these issues, we propose EviRCOD, an integrated framework consisting of three core components: (1) a Reference-Guided Deformable Encoder (RGDE) that employs hierarchical reference-driven modulation and multi-scale deformable aggregation to inject semantic priors and align cross-scale representations; (2) an Uncertainty-Aware Evidential Decoder (UAED) that incorporates Dirichlet evidence estimation into hierarchical decoding to model uncertainty and propagate confidence across scales; and (3) a Boundary-Aware Refinement Module (BARM) that selectively enhances ambiguous boundaries by exploiting low-level edge cues and prediction confidence. Experiments on the Ref-COD benchmark demonstrate that EviRCOD achieves state-of-the-art detection performance while providing well-calibrated uncertainty estimates. Code is available at: https://github.com/blueecoffee/EviRCOD.
title EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10894