As far as we know, there only exists one large camouflaged object testing dataset, the COD10K, while the sizes of other testing datasets are less than 300. We then contribute another camouflaged object testing dataset, namely NC4K, which includes 4,121 images downloaded from the Internet. The new testing dataset can be used to evaluate the generalization ability of existing models.
Variants: NC4K
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Camouflaged Object Segmentation | FOCUS | FOCUS: Towards Universal Foreground Segmentation | 2025-01-09 |
| Camouflaged Object Segmentation | BiRefNet | Bilateral Reference for High-Resolution Dichotomous … | 2024-01-07 |
| Camouflaged Object Segmentation | ZoomNeXt-PVTv2-B5 | ZoomNeXt: A Unified Collaborative Pyramid … | 2023-10-31 |
| Camouflaged Object Segmentation | ZoomNeXt-PVTv2-B4 | ZoomNeXt: A Unified Collaborative Pyramid … | 2023-10-31 |
| Camouflaged Object Segmentation | ZoomNeXt-ResNet-50 | ZoomNeXt: A Unified Collaborative Pyramid … | 2023-10-31 |
| Camouflaged Object Segmentation | SINetV2-Res2Net-50 | Concealed Object Detection | 2021-02-20 |
Recent papers with results on this dataset: