Camouflaged Object Segmentation
Camouflaged object segmentation (COS) or Camouflaged object detection (COD), which was originally promoted by T.-N. Le et al. (2017), aims to identify objects that conceal their texture into the surrounding environment. The high intrinsic similarities between the target object and the background make COS/COD far more challenging than the traditional object segmentation task. Also, refer to the online benchmarks on CAMO dataset, COD dataset, and online demo.
( Image source: Anabranch Network for Camouflaged Object Segmentation )
Papers
Showing 1–10 of 47 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FOCUS | S-Measure | 0.91 | — | Unverified |
| 2 | BiRefNet | S-Measure | 0.9 | — | Unverified |
| 3 | ZoomNeXt-PVTv2-B5 | S-Measure | 0.89 | — | Unverified |
| 4 | ZoomNeXt-PVTv2-B4 | S-Measure | 0.89 | — | Unverified |
| 5 | EVPv2 | S-Measure | 0.85 | — | Unverified |
| 6 | EVPv1 | S-Measure | 0.85 | — | Unverified |
| 7 | SAMFusion | Weighted F-Measure | 0.83 | — | Unverified |
| 8 | ZoomNeXt-ResNet-50 | S-Measure | 0.83 | — | Unverified |
| 9 | SINet-V2 | S-Measure | 0.82 | — | Unverified |
| 10 | MirrorNet-ResNeXt152 | S-Measure | 0.79 | — | Unverified |