List your company

Open-Vocabulary Segmentation on Pascal VOC

79.52mIoUCoM-PT
20.988836.184451.3866.5756Aug 27, 2024Dec 15, 2024Apr 5, 2025Jul 25, 2025Nov 12, 2025Mar 3, 2026Jun 22, 2026

Evaluation results

MethodLinks
CoM-PTBackbone=ViT-L/16, PT Method=CoM-PT, Fine-tuning Protocol=SAN [70]2026.0479.52—
CoM-PTBackbone=ViT-B/16, PT Method=CoM-PT, Fine-tuning Protocol=SAN [70]2026.0476.96—
BaselineBackbone=ViT-L/16, PT Method=Baseline, Fine-tuning Protocol=SAN [70]2026.0469.76—
BaselineBackbone=ViT-B/16, PT Method=Baseline, Fine-tuning Protocol=SAN [70]2026.0468.59—
LoftUp2026.0665.2187.89
AnyUp2026.0663.6787.5
JAFAR2026.0663.5287.43
RaysUp2026.0663.2887.34
Bilinear2026.0659.7185.87
ProMaCVenue=Ours, Segmentation Annotation=-, Extra Text pairs=-2024.0859.3—
FeatUp2026.0654.9684.02
OVSegmentorVenue=CVPR23, Segmentation Annotation=-, Extra Text pairs=CC12M [7]2024.0853.8—
SegCLIPVenue=ICML23, Segmentation Annotation=COCO [35], Extra Text pairs=CC [48]2024.0852.6—
ViewCoVenue=ICLR23, Segmentation Annotation=-, Extra Text pairs=CC12M [7], YFCC14M [53]2024.0852.4—
GroupViTVenue=CVPR22, Segmentation Annotation=-, Extra Text pairs=CC12M [7], YFCC14M [53]2024.0852.3—
TCLVenue=CVPR23, Segmentation Annotation=-, Extra Text pairs=CC3M [48], CC12M [7]2024.0851.2—
MaskCLIPVenue=ECCV22, Segmentation Annotation=-, Extra Text pairs=-2024.0838.8—
JAFARUpsampling=JAFAR, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.0635.744.93
FeatUpUpsampling=FeatUp, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.0632.2739.78
BilinearUpsampling=Bilinear, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.0627.8735.27
NearestUpsampling=Nearest, Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.0624.1330.8
Large Image (×2)Upsampling=Large Image (×2), Zero-shot=true, Backbone=CLIP-ViT-B/16, Framework=MaskCLIP [9]2025.0623.2432.16