COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptions
Quick Take
The COD10K-C benchmark evaluates camouflaged object detection under real-world corruptions, revealing significant performance drops. Models like SINet-v2 lost 18.5 Dice points under motion blur, while RobustCODLite maintained 92.3% of its clean score, outperforming others in severe conditions. This benchmark aims to enhance robustness in camouflaged object detection research.
Key Points
- COD10K-C includes 8 corruption types and 5 severity levels, totaling 81,040 evaluation pairs.
- RobustCODLite retains 92.3% of its clean Dice score under corruption, outperforming SINet-v2 and others.
- Motion blur and Gaussian blur are the most detrimental, causing significant performance drops.
- The benchmark will be available on GitHub to support future research in this area.
- Standard benchmarks often fail to account for real-world image corruptions.
Article Content
From source RSS / original summaryarXiv:2606. 02603v1 Announce Type: new Abstract: 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records
Plan2Map introduces a 208-case benchmark for reconstructing geospatial boundaries from UK planning documents. The GeoPlanAgent system achieves a mean IoU of 0.736, significantly outperforming baseline models, highlighting the challenges in localization and map registration.
