Real-World Marine Animal Segmentation
We construct a new large-scale real-world MAS data set for conducting extensive experiments. It consists of over 3000 images with various underwater scenes and objects. Each image is annotated with an object-level mask and assigned to a category.
Variants: RMAS
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Segmentation | SAM2-UNet | SAM2-UNet: Segment Anything 2 Makes … | 2024-08-16 |
| Image Segmentation | MAS-SAM | MAS-SAM: Segment Any Marine Animal … | 2024-04-24 |
| Image Segmentation | ZoomNet | Zoom In and Out: A … | 2022-03-05 |
Recent papers with results on this dataset: