List your company
ResearchFormerly WizWand

Semantic Segmentation on ADE-20k A-847 (test)

15.7mIoUDPSeg
1.9725.5369.112.664Oct 20, 2023Jan 23, 2024Apr 28, 2024Aug 2, 2024Nov 5, 2024Feb 9, 2025May 16, 2025
Updated 8mo ago

Evaluation results

MethodLinks
DPSegVLM=ConvNeXt-L, Inference Mode=II, Training Dataset=COCO-Stuff2025.0515.7
CAT-SegVLM=SILC-C-L/162023.1015
DPSegVLM=ConvNeXt-L, Inference Mode=I, Training Dataset=COCO-Stuff2025.0514.9
FC-CLIPVLM=ConvNeXt-L, Training Dataset=COCO Panoptic [20]2025.0514.8
SCANVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0514
SEDVLM=ConvNeXt-L, Training Dataset=COCO-Stuff2025.0513.9
SANVLM=ViT-L/14, Training Dataset=COCO-Stuff2025.0513.7
EBSegVLM=ViT-L/14, Training Dataset=COCO-Stuff2025.0513.7
CAT-SegVLM=SILC-S-B/162023.1013.5
CAT-SegVLM=SILC-C-B/162023.1013.4
CAT-SegVLM=CLIP-G/142023.1013.3
USE+SAMVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0513.3
DPSegVLM=ConvNeXt-B, Inference Mode=II, Training Dataset=COCO-Stuff2025.0512.5
DPSegVLM=ConvNeXt-B, Inference Mode=I, Training Dataset=COCO-Stuff2025.0512
SEDVLM=ConvNeXt-B, Training Dataset=COCO-Stuff2025.0511.4
EBSegVLM=ViT-B/16, Training Dataset=COCO-Stuff2025.0511.1
ODISEVLM=ViT-L/14, Training Dataset=COCO Panoptic [20]2025.0511.1
CAT-SegVLM=CLIP-L/142023.1010.8
SCANVLM=ViT-B/16, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0510.8
CAT-SegVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0510.8
SANVLM=ViT-B/16, Training Dataset=COCO-Stuff2025.0510.1
OVSegVLM=CLIP-L/142023.109
OVSegVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff+COCO Caption2025.059
CAT-SegVLM=CLIP-B/162023.108.4
CAT-SegVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.058.4
Ding et al.VLM=ViT-L/14, Training Dataset=COCO Panoptic [20]2025.058.2
OpenSegVLM=ALIGN, Backbone=Eff-B7 [44], Training Dataset=COCO Panoptic [20] + Loc. Narr. [36]2025.058.1
OVSegVLM=CLIP-B/162023.107.1
ZSsegVLM=CLIP-L/142023.107.1
OVSegVLM=ViT-B/16, Backbone=ResNet-101c, Training Dataset=COCO-Stuff+COCO Caption2025.057.1
ZSsegVLM=CLIP-B/162023.107
SimSegVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.057
ZegFormerVLM=CLIP-B/162023.105.6
ZegFormerVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.055.6
OpenSegVLM=ALIGN, Backbone=ResNet-101, Training Dataset=COCO Panoptic [20] + Loc. Narr. [36]2025.054.4
Han et al.VLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO Panoptic [20]2025.053.5
LSeg+VLM=ALIGN RN-101, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.052.5