提升隐蔽目标检测的精准度与可靠性，通过证据引导的解码机制实现更稳健的边界分割。
EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
- 用参考信息引导分层变形编码，增强语义对齐与多尺度特征融合。
- 引入狄利克雷证据估计，实现跨尺度不确定性建模与置信度传播。
- 结合低级边缘线索与置信度，精准优化模糊边界区域。
指代式隐蔽目标检测（Ref-COD）旨在利用类别对齐的参考信息，在查询图像中分割特定的隐蔽目标。尽管近期取得进展，现有方法仍面临参考-目标语义对齐不足、显式不确定性建模缺失及边界保持鲁棒性差的问题。为此，我们提出EviRCOD，一个包含三个核心组件的集成框架：(1) 参考引导的可变形编码器（RGDE），采用分层参考驱动调制与多尺度可变形聚合，注入语义先验并对齐跨尺度表示；(2) 不确定性感知的证据解码器（UAED），在分层解码中引入狄利克雷证据估计，建模不确定性并跨尺度传播置信度；(3) 边界感知精化模块（BARM），通过利用低级边缘线索与预测置信度，选择性增强模糊边界。在Ref-COD基准上的实验表明，EviRCOD达到当前最优检测性能，同时提供校准良好的不确定性估计。代码已公开于：https://github.com/blueecoffee/EviRCOD。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。