| Paper | Code | J&F | ModelName | ReleaseDate |
|---|---|---|---|---|
| SAM 3: Segment Anything with Concepts | ✓ Link | 83.5 | SAM 3 (zero-shot) (extra data) | 2025-11-20 |
| SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree | ✓ Link | 81.1 | SAM2.1Long-L (extra data) | 2024-10-21 |
| SAM 2: Segment Anything in Images and Videos | ✓ Link | 77.9 | SAM 2 (Hiera-L) (extra data) | 2024-08-01 |
| Efficient Video Object Segmentation and Tracking with Recurrent Dynamic Submodel | 77.6 | SAM2 + RDS 0.9 | 2026-06-03 | |
| EdgeTAM: On-Device Track Anything Model | ✓ Link | 72.3 | EdgeTAM (extra data) | 2025-01-13 |
| MobileSAM2: Lightweight Segment Anything in Images and Videos via Hypergraphical Knowledge Distillation | 66.4 | MobileSAM2-23M | 2026-09-08 |