Referring Expression Segmentation on RefCOCOg Google (val)
67.2gIoUTarot-SAM3
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Tarot-SAM3Version=Qwen2.5-VL 7B, Trained on RES=false2026.04 | 67.2 | — | |
| EVOL-SAM3Version=Qwen2.5-VL 7B, Trained on RES=false2026.04 | 65.9 | — | |
| Tarot-SAM3Version=Qwen2.5-VL 3B, Trained on RES=false2026.04 | 65.1 | — | |
| EVOL-SAM3Version=Qwen2.5-VL 3B, Trained on RES=false2026.04 | 64 | — | |
| SAM 3 AgentVersion=Qwen2.5-VL 7B, Trained on RES=false2026.04 | 59.7 | — | |
| LGD+DINOVersion=ViT-B/32, Trained on RES=false2026.04 | 52.5 | — | |
| TASVersion=ResNet-50, Trained on RES=false2026.04 | 48.7 | — | |
| TASVersion=ViT-B/32, Trained on RES=false2026.04 | 48.1 | — | |
| Pseudo-RISVersion=ETRIS, Trained on RES=false2026.04 | 46.8 | — | |
| IterRPrimeEVersion=N/A, Trained on RES=false2026.04 | 45.8 | — | |
| Ref-DiffVersion=VAE, Trained on RES=false2026.04 | 44.3 | — | |
| GL-CLIPVersion=ResNet-50, Trained on RES=false2026.04 | 44 | — | |
| Pseudo-RISVersion=CRIS, Trained on RES=false2026.04 | 43.8 | — | |
| GL-CLIPVersion=ViT-B/32, Trained on RES=false2026.04 | 42.7 | — | |
| CaRVersion=ViT-B/16, Trained on RES=false2026.04 | 36.6 | — | |
| PolyFormerLabel-Rate Mask=100%, Label-Rate BBox=100%, Vis. Backbone=Swin-B, Supervision Type=Fully Supervised, Extra Training Data=true2024.07 | — | 69.36 | |
| ResTRLabel-Rate Mask=100%, Label-Rate BBox=100%, Vis. Backbone=ViT-B, Supervision Type=Fully Supervised2024.07 | — | 54.48 | |
| SAFARILabel-Rate Mask=100%, Label-Rate BBox=100%, Vis. Backbone=Swin-B, Supervision Type=Fully Supervised, Extra Training Data=true2024.07 | — | 70.48 | |
| VLTLabel-Rate Mask=100%, Label-Rate BBox=100%, Vis. Backbone=DN53, Supervision Type=Fully Supervised2024.07 | — | 49.76 |