EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection

TL;DR

EviRCOD introduces an integrated framework with three novel components for improved referring camouflaged object detection, addressing semantic alignment, uncertainty modeling, and boundary refinement, achieving state-of-the-art results.

Contribution

The paper presents EviRCOD, a novel framework combining hierarchical reference-guided encoding, uncertainty-aware decoding, and boundary refinement for better camouflaged object detection.

Findings

Achieves state-of-the-art performance on Ref-COD benchmark.

Provides well-calibrated uncertainty estimates.

Effectively enhances ambiguous boundaries using low-level cues.

Abstract

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.