超越外观：基于几何结构的伪装目标检测
Beyond Appearance: Camouflaged Object Detection via Geometric Structure
把单目深度估计模型通过稀疏混合专家适配器迁移到伪装目标检测，并用几何-语义融合模块把深度几何线索注入分割特征，为「深度先验跨任务迁移」提供了一个可复用的适配与融合范式。
原文依据 a Sparse Mixture-of-Experts Adapter (SMEA) that enables MDE to learn semantic information unique to camouflaged scenes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论深度先验提供了显著的几何结构，有利于伪装目标检测（COD），但直接使用单目深度估计（MDE）会造成任务错配，仍然无法识别伪装目标。为解决这一问题，我们提出 Depth Segment Anything Model（DepthSAM），一种专门为缓解该错配而设计的 MDE 适配方法。DepthSAM 包含两项核心创新：（1）稀疏混合专家适配器（SMEA），使 MDE 能够学习伪装场景特有的语义信息；（2）几何-语义融合模块（GSFM），高效地将几何线索与高层语义相融合。借助这些组件，DepthSAM 在伪装环境中实现了稳健的语义理解，并能准确分割伪装目标。大量实验表明，DepthSAM 在三个主要基准上取得了新的 SOTA 性能。例如，在 COD10K 上，其 S_α 与 F_b^ω 指标分别超过最佳竞争方法 3.0% 和 4.3%。
英文原文摘要 1048 字符
Depth priors provide salient geometric structure that benefits camouflaged object detection (COD), but directly using Monocular Depth Estimation (MDE) causes a task misalignment that still fails to identify camouflaged objects.To address this issue, we propose the Depth Segment Anything Model (DepthSAM), a MDE-adapted method specifically designed to mitigate this misalignment.DepthSAM incorporates two core innovations: (1) a Sparse Mixture-of-Experts Adapter (SMEA) that enables MDE to learn semantic information unique to camouflaged scenes, and (2) a Geometric-Semantic Fusion Module (GSFM) that efficiently integrates geometric cues with high-level semantics. With these components, DepthSAM achieves both robust semantic understanding in camouflaged environments and accurate segmentation of camouflaged objects.Extensive experiments show that DepthSAM achieves new SOTA performance on three major benchmarks. For example, on COD10K, its S_ \alpha and F_ b ^ \omega metrics surpass the best competing methods by 3.0% and 4.3%, respectively.