Segment Anything without Supervision
–Neural Information Processing Systems
The Segmentation Anything Model (SAM) requires labor-intensive data labeling. We present Unsupervised SAM (UnSAM) for promptable and automatic wholeimage segmentation that does not require human annotations. UnSAM utilizes a divide-and-conquer strategy to "discover" the hierarchical structure of visual scenes.
Neural Information Processing Systems
Mar-27-2025, 15:56:34 GMT
- Country:
- Europe > Switzerland
- North America > United States (0.28)
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Government (0.46)
- Technology: