Unsupervised Semantic Segmentation With 7
Métriques
mIoU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | mIoU | Paper Title | Repository |
|---|---|---|---|
| ProxyCLIP | 83.3 | ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation | |
| MaskCLIP | 74.9 | Extract Free Dense Labels from CLIP | |
| TCL | 83.2 | Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs | |
| GroupViT (RedCaps) | 79.7 | GroupViT: Semantic Segmentation Emerges from Text Supervision | |
| Trident | 88.7 | Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation | |
| TagAlign | 87.9 | TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification | |
| COSMOS ViT-B/16 | 77.7 | COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training | |
| ReCo | 57.7 | ReCo: Retrieve and Co-segment for Zero-shot Transfer | - |
0 of 8 row(s) selected.