List your company
ResearchFormerly WizWand

Semantic Segmentation on Pascal Context 459 classes (test)

25.8mIoUCAT-Seg
4.3769.93815.521.062Sep 30, 2023Oct 3, 2023Oct 6, 2023Oct 10, 2023Oct 13, 2023Oct 16, 2023Oct 20, 2023
Updated 8mo ago

Evaluation results

MethodLinks
CAT-SegVLM=SILC-C-L/162023.1025.8
CAT-SegVLM=SILC-C-B/162023.1022
CAT-SegVLM=SILC-S-B/162023.1021.9
CAT-SegVLM=CLIP-G/142023.1021.4
CAT-SegVLM=CLIP-L/142023.1020.4
CAT-SegVLM=CLIP-B/162023.1016.6
FreeSeg + MAFTOpen-vocabulary setting=true, Proposal Generator Backbone=ResNet101, CLIP Backbone=ViT-B/16, Module=IP-CLIP Encoder2023.0912.8
OVSegVLM=CLIP-L/142023.1012.4
OpenSegOpen-vocabulary setting=true, Additional training data=true2023.0912.2
OVSegOpen-vocabulary setting=true2023.0911
OVSegVLM=CLIP-B/162023.1011
ZegFormerVLM=CLIP-B/162023.1010.4
ZSsegVLM=CLIP-L/142023.1010.2
FreeSegOpen-vocabulary setting=true, Proposal Generator Backbone=ResNet101, CLIP Backbone=ViT-B/162023.096.4
LSeg+Open-vocabulary setting=true2023.095.2