Open-Vocabulary Segmentation on Pascal VOC
79.52mIoUCoM-PT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoM-PTBackbone=ViT-L/16, PT Method=CoM-PT, Fine-tuning Protocol=SAN [70]2026.04 | 79.52 | — | |
| CoM-PTBackbone=ViT-B/16, PT Method=CoM-PT, Fine-tuning Protocol=SAN [70]2026.04 | 76.96 | — | |
| BaselineBackbone=ViT-L/16, PT Method=Baseline, Fine-tuning Protocol=SAN [70]2026.04 | 69.76 | — | |
| BaselineBackbone=ViT-B/16, PT Method=Baseline, Fine-tuning Protocol=SAN [70]2026.04 | 68.59 | — | |
| LoftUp2026.06 | 65.21 | 87.89 | |
| AnyUp2026.06 | 63.67 | 87.5 | |
| JAFAR2026.06 | 63.52 | 87.43 | |
| RaysUp2026.06 | 63.28 | 87.34 | |
| Bilinear2026.06 | 59.71 | 85.87 | |
| ProMaCVenue=Ours, Segmentation Annotation=-, Extra Text pairs=-2024.08 | 59.3 | — | |
| FeatUp2026.06 | 54.96 | 84.02 | |
| OVSegmentorVenue=CVPR23, Segmentation Annotation=-, Extra Text pairs=CC12M [7]2024.08 | 53.8 | — | |
| SegCLIPVenue=ICML23, Segmentation Annotation=COCO [35], Extra Text pairs=CC [48]2024.08 | 52.6 | — | |
| ViewCoVenue=ICLR23, Segmentation Annotation=-, Extra Text pairs=CC12M [7], YFCC14M [53]2024.08 | 52.4 | — | |
| GroupViTVenue=CVPR22, Segmentation Annotation=-, Extra Text pairs=CC12M [7], YFCC14M [53]2024.08 | 52.3 | — | |
| TCLVenue=CVPR23, Segmentation Annotation=-, Extra Text pairs=CC3M [48], CC12M [7]2024.08 | 51.2 | — | |
| MaskCLIPVenue=ECCV22, Segmentation Annotation=-, Extra Text pairs=-2024.08 | 38.8 | — | |
| JAFARUpsampling=JAFAR, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.06 | 35.7 | 44.93 | |
| FeatUpUpsampling=FeatUp, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.06 | 32.27 | 39.78 | |
| BilinearUpsampling=Bilinear, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.06 | 27.87 | 35.27 | |
| NearestUpsampling=Nearest, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.06 | 24.13 | 30.8 | |
| Large Image (×2)Upsampling=Large Image (×2), Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.06 | 23.24 | 32.16 |