提出首个伪装目标检测抗干扰基准，评估模型在真实图像退化下的表现。
COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptions
- 构建包含40种退化条件的COD10K-C基准，覆盖8类自然图像损伤。
- 轻量模型RobustCODLite在强退化下仍保持92.3%的检测性能，优于现有模型。
- 揭示运动模糊和高斯模糊对检测性能影响最大，适合关注实际应用的开发者。
伪装目标检测虽有显著进展，但主流基准仅在干净图像上评估，缺乏真实性。本文提出基于COD10K的抗退化基准COD10K-C，包含8类图像退化和5个严重等级，共40种条件，总计81,040个评估样本。评估SINet-v2、PFNet、ZoomNet及轻量模型RobustCODLite发现，所有模型在退化图像上性能明显下降。运动模糊与高斯模糊造成最严重损失，其中SINet-v2在运动模糊下Dice分数下降18.5点；亮度与雾化影响较小。RobustCODLite采用退化增强、频率先验分支与不确定性一致性损失，在退化条件下保留92.3%的干净图像性能，优于SINet-v2（87.7%）、ZoomNet（84.8%）和PFNet（84.1%）。在最难退化条件下，其性能可匹敌甚至超越在干净数据上表现更好的模型。项目代码将开源，推动鲁棒伪装目标检测研究。
原文摘要 · Abstract (English)
Camouflaged object detection has improved substantially, but most standard benchmarks evaluate models only on clean images. This is not realistic because real cameras often capture blur, sensor noise, weather effects, and compression artifacts. We present COD10K-C, a corruption robustness benchmark based on COD10K. It includes 8 corruption types and 5 severity levels, giving 40 conditions and 81,040 evaluation pairs in total. We evaluate three popular camouflaged object detection models, SINet-v2, PFNet, and ZoomNet, as well as a lightweight model called RobustCODLite. All models show clear performance drops on corrupted images. Motion blur and Gaussian blur cause the largest drops, with SINet-v2 losing 18.5 Dice points under motion blur. Brightness and fog are less harmful. RobustCODLite uses corruption augmentation, a frequency-prior branch, and an uncertainty-consistency loss. It retains 92.3% of its clean Dice score under corruption, compared with 87.7% for SINet-v2, 84.8% for ZoomNet, and 84.1% for PFNet. On the hardest corruptions, RobustCODLite matches or outperforms models that perform better on clean data. We will release the COD10K-C GitHub repository to support future research in robust camouflaged object detection.
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。