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

2026-04-12

AI Summary

This work addresses key challenges in referring camouflaged object detection—namely, difficulties in semantic alignment between reference expressions and target objects, insufficient modeling of prediction uncertainty, and ambiguous object boundaries—by proposing the EviRCOD framework. EviRCOD introduces Dirichlet evidence theory to this task for the first time, employing a reference-guided deformable encoder to achieve cross-scale semantic alignment. It further incorporates an evidence-based uncertainty-aware decoder to explicitly model prediction confidence and designs a boundary-aware refinement module to enhance edge details. Evaluated on the Ref-COD benchmark, EviRCOD achieves state-of-the-art performance while producing well-calibrated uncertainty estimates, significantly improving both detection accuracy and boundary quality.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Object Detection & Categorization
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

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.

Problem

• Referring Camouflaged Object Detection
• semantic alignment
• uncertainty modeling
• boundary preservation

Innovation

• Evidence-Guided Decoding
• Reference-Guided Deformable Encoder
• Uncertainty-Aware Evidential Decoder
• Boundary-Aware Refinement
• Referring Camouflaged Object Detection