Deep Gradient Learning for Efficient Camouflaged Object Detection
About
This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential connection is the gradient-induced transition, representing a soft grouping between context and texture features. Benefiting from the simple but efficient framework, DGNet outperforms existing state-of-the-art COD models by a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80 fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR$_{21}$ with only 6.82% parameters. Application results also show that the proposed DGNet performs well in polyp segmentation, defect detection, and transparent object segmentation tasks. Codes will be made available at https://github.com/GewelsJI/DGNet.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Camouflaged Object Detection | COD10K | S-measure (S_alpha)0.822 | 178 | |
| Camouflaged Object Detection | NC4K | Sm85.7 | 58 | |
| Camouflaged Object Segmentation | CAMO (test) | S-measure (S_alpha)0.839 | 56 | |
| Camouflaged Object Segmentation | NC4K | Fw_beta78.4 | 41 | |
| Referring Camouflaged Object Detection | R2C7K | Sm82.1 | 32 | |
| Camouflaged Object Detection | CAMO | MAE5.7 | 22 | |
| Camouflaged Object Detection | Chameleon | MAE0.029 | 22 | |
| Referring Camouflaged Object Detection | R2C7K Single Object | Sm0.827 | 16 |