SPEGNet：面向伪装目标检测的协同感知引导网络
SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection
AI总结：
针对现有伪装目标检测方法堆叠组件带来计算负担、丢失精细细节的问题，提出统一架构SPEGNet，通过通道校准与空间增强融合多尺度特征，结合尺度自适应边缘调制，在多个基准上实现高精度与实时推理的平衡。
摘要：
伪装目标检测旨在分割具有内在相似性和边缘断裂特征的目标。当前检测方法依赖堆叠复杂组件，各类方法分别独立添加边界模块、注意力机制、多尺度处理器等组件，这种堆叠方式带来了计算负担却未获得相应的性能提升。为控制复杂度，这些方法在降低的分辨率下进行处理，丢失了对伪装检测至关重要的精细细节。我们提出SPEGNet（协同感知引导网络），通过统一化设计解决组件碎片化问题。该架构通过通道校准与空间增强融合多尺度特征，边界信息直接从富含上下文的表征中生成，保持语义-空间对齐。渐进式细化模块实现尺度自适应边缘调制，在中间分辨率下作用达到峰值，该设计在边界精度与区域一致性之间取得了平衡。SPEGNet在CAMO数据集上达到0.887的$S_α$指标，在COD10K上为0.890，在NC4K上为0.895，且具备实时推理速度。我们的方法在不同尺度目标上均表现优异，涵盖微小复杂目标到大型图案相似目标，同时可处理遮挡与边界模糊问题。代码、模型权重与结果可在https://github.com/Baber-Jan/SPEGNet获取。
英文摘要：
Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and multi-scale processors independently. This accumulation creates a computational burden without proportional gains. To manage this complexity, they process at reduced resolutions, eliminating fine details essential for camouflage. We present SPEGNet, addressing fragmentation through a unified design. The architecture integrates multi-scale features via channel calibration and spatial enhancement. Boundaries emerge directly from context-rich representations, maintaining semantic-spatial alignment. Progressive refinement implements scale-adaptive edge modulation with peak influence at intermediate resolutions. This design strikes a balance between boundary precision and regional consistency. SPEGNet achieves 0.887 $S_α$ on CAMO, 0.890 on COD10K, and 0.895 on NC4K, with real-time inference speed. Our approach excels across scales, from tiny, intricate objects to large, pattern-similar ones, while handling occlusion and ambiguous boundaries. Code, model weights, and results are available on \href{https://github.com/Baber-Jan/SPEGNet}{https://github.com/Baber-Jan/SPEGNet}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
