EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
For researchers in camouflaged object detection, this work provides a novel framework that improves semantic alignment and uncertainty modeling, though it is an incremental improvement over existing methods.
EviRCOD tackles referring camouflaged object detection by integrating reference-guided encoding, uncertainty-aware evidential decoding, and boundary-aware refinement, achieving state-of-the-art performance on the Ref-COD benchmark.
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.