SA-1B consists of 11M diverse, high resolution, licensed, and privacy protecting images and 1.1B high-quality segmentation masks.
Source: Segment Anything
Image Source: Segment Anything
Variants: SA-1B
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Segmentation | unSAM+ (Semi-supervised) | Segment Anything without Supervision | 2024-06-28 |
| Segmentation | SAM | Segment Anything without Supervision | 2024-06-28 |
Recent papers with results on this dataset: