Panoptic Segmentation on COCO 2017 (val)
59.9PQMask2Former
Evaluation Results
| Method | Links | ||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Mask2FormerBackbone=ViT-Adapter-g+, Pre-training=DINOv2, Params=1216M, Input size=1280x12802025.03 | 59.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 13,790 | 6 | — | |
| Mask2Former+Backbone=ViT-Adapter-L+, Pre-training=DINOv2, Params=354M, Input size=1280x12802025.03 | 59.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 4,817 | 10 | — | |
| Mask DINOBackbone=Swin-L [38], #Params=223M, Extra Data=true, Training Protocol=Individual Training2022.11 | 59.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EoMTBackbone=ViT-g, Pre-training=DINOv2, Params=1171M, Input size=1280x12802025.03 | 59.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 12,712 | 12 | — | |
| MaskDINOBackbone=Swin-L, Pre-training=IN21K, Params=223M, Input size=800x8002025.03 | 58.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,326 | 14 | — | |
| EoMTBackbone=ViT-L, Pre-training=DINOv2, Params=322M, Input size=1280x12802025.03 | 58.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 4,146 | 30 | — | |
| VAN-B6Backbone=VAN-B6, Base Architecture=Mask2Former [113], Query type=200 queries, Epochs=50, Pre-trained=ImageNet-22K2022.02 | 58.2 | — | — | 64.8 | — | — | 48.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| kMaX-DeepLabBackbone=ConvNeXt-L [39], #Params=232M, Extra Data=true, Training Protocol=Individual Training2022.11 | 58.1 | — | — | 64.3 | — | — | 48.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MP-Formerbackbone=Swin-L, query type=200 queries, epochs=72, #params.=216M, FLOPs=868G, fps=42023.03 | 58.1 | — | — | 64.4 | — | — | 48.4 | — | — | — | — | — | — | — | — | — | — | 67.6 | 48.9 | — | — | — | — | — | — | — | — | — | |
| kMaX-DeepLabBackbone=ConvNeXt-L [39], #Params=232M, Extra Data=false, Training Protocol=Individual Training2022.11 | 58 | — | — | 64.2 | — | — | 48.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OneFormerBackbone=DINAT-L [21], #Params=223M, Extra Data=false, Training Protocol=Joint Training2022.11 | 58 | — | — | 64.3 | — | — | 48.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| kMaX-DeepLab*Backbone=ConvNeXt-L, #Params=232M, #FLOPs=749G, #Queries=256, Epochs=812022.11 | 58 | — | — | 64.2 | — | — | 48.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OneFormerBackbone=DINAT-L+, #Params=223M, #FLOPs=736G, #Queries=150, Epochs=1002022.11 | 58 | — | — | 64.3 | — | — | 48.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| kMaX-DeepLabBackbone=ConvNext-L, Pre-training=IN21K, Params=232M, Input size=1281x12812025.03 | 58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OneFormer+Backbone=DINAT-L, Pre-training=IN21K, Params=223M, Input size=800x8002025.03 | 58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 736 | 20 | — | |
| OneFormerBackbone=Swin-L [38], #Params=219M, Extra Data=false, Training Protocol=Joint Training2022.11 | 57.9 | — | — | 64.4 | — | — | 48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| kMaX-DeepLab*Backbone=ConvNeXt-L, #Params=232M, #FLOPs=749G, #Queries=128, Epochs=812022.11 | 57.9 | — | — | 64 | — | — | 48.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OneFormerBackbone=Swin-L+, #Params=219M, #FLOPs=891G, #Queries=150, Epochs=1002022.11 | 57.9 | — | — | 64.4 | — | — | 48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Formerbackbone=Swin-L*, query type=100 queries, epochs=100, #params=216M, FLOPS=868G, fps=42021.12 | 57.8 | — | — | 64.2 | — | — | 48.1 | — | — | — | — | — | — | — | — | — | 48.6 | 67.4 | — | — | — | — | — | — | — | — | — | — | |
| Swin-LBackbone=Swin-L, Base Architecture=Mask2Former [113], Query type=200 queries, Epochs=50, Pre-trained=ImageNet-22K2022.02 | 57.8 | — | — | 64.2 | — | — | 48.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Former2022.05 | 57.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Former-PanopticBackbone=Swin-L [38], #Params=216M, Extra Data=false, Training Protocol=Individual Training2022.11 | 57.8 | — | — | 64.2 | — | — | 48.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Former-PanopticBackbone=Swin-L, #Params=216M, #FLOPs=875G, #Queries=200, Epochs=1002022.11 | 57.8 | — | — | 64.2 | — | — | 48.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Formerbackbone=Swin-L, query type=200 queries, epochs=100, #params.=216M, FLOPs=868G, fps=42023.03 | 57.8 | — | — | 64.2 | — | — | 48.1 | — | — | — | — | — | — | — | — | — | — | 67.4 | 48.6 | — | — | — | — | — | — | — | — | — | |
| Mask2Formermodel category=specialist model, venue=CVPR'222023.04 | 57.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2FormerBackbone=Swin-L, Pre-training=IN21K, Params=216M, Input size=800x8002025.03 | 57.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 868 | 24 | — | |
| Mask2FormerBackbone=ViT-Adapter-g+, Pre-training=DINOv2, Params=1209M, Input size=640x6402025.03 | 57.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 2,510 | 20 | — | |
| Mask2Former+Backbone=ViT-Adapter-L+, Pre-training=DINOv2, Params=349M, Input size=640x6402025.03 | 57.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 830 | 29 | — | |
| EoMTBackbone=ViT-g, Pre-training=DINOv2, Params=1164M, Input size=640x6402025.03 | 57 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 2,261 | 55 | — | |
| SegMAN-S EncoderEncoder=SegMAN-S Encoder, Parameters=48.3M, GFLOPs=2832024.12 | 56.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EoMTBackbone=ViT-L, Pre-training=DINOv2, Params=316M, Input size=640x6402025.03 | 56 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 669 | 128 | — | |
| Panoptic SegFormerBackbone=Swin-L [38], #Params=221M, Extra Data=false, Training Protocol=Individual Training2022.11 | 55.8 | — | — | 61.7 | — | — | 46.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Panoptic SegFormerBackbone=Swin-L, #Params=221M, #FLOPs=816G, #Queries=353, Epochs=242022.11 | 55.8 | — | — | 61.7 | — | — | 46.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CMT-DeepLab (iter 200k)backbone=Axial-R104-RFN, TTA=false, params=270.3M2022.06 | 55.3 | — | — | 61 | — | — | 46.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CMT-DeepLabbackbone=Axial-R104-RFN, TTA=false, params=270.3M2022.06 | 55.1 | — | — | 60.6 | — | — | 46.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VAN-B2Backbone=VAN-B2, Base Architecture=Mask2Former [113], Query type=100 queries, Epochs=50, Pre-trained=ImageNet-1K2022.02 | 54.9 | — | — | 61.2 | — | — | 45.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiT-B2Encoder=MiT-B2, Parameters=48.5M, GFLOPs=3152024.12 | 54.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-NetBackbone=Swin-L, Box-free=true, NMS-free=true, Epochs=362021.06 | 54.6 | — | — | 60.2 | — | — | 46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-Netbackbone=Swin-L+, query type=100 queries, epochs=362021.12 | 54.6 | — | — | 60.2 | — | — | 46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-NetBackbone=Swin-L+, #Queries=100, Epochs=362022.11 | 54.6 | — | — | 60.2 | — | — | 46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-Netbackbone=Swin-L, query type=100 queries, epochs=362023.03 | 54.6 | — | — | 60.2 | — | — | 46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CMT-DeepLabbackbone=Axial-R104, TTA=false, params=135.2M2022.06 | 54.1 | — | — | 58.8 | — | — | 47.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ReMaxBackbone=Res502024.04 | 53.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Swin-TBackbone=Swin-T, Base Architecture=Mask2Former [113], Query type=100 queries, Epochs=50, Pre-trained=ImageNet-1K2022.02 | 53.2 | — | — | 59.3 | — | — | 44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CleanBackbone=Swin-T2024.10 | 53.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 43.3 | 63.2 | — | — | — | — | — | — | — | — | — | — | |
| CMT-DeepLabbackbone=Axial-R50 (ImageNet-22K), TTA=false, params=94.9M2022.06 | 53 | — | — | 57.7 | — | — | 45.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ResNet50Encoder=ResNet50, Parameters=52M, GFLOPs=2862024.12 | 53 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MP-Formerbackbone=R101, query type=100 queries, epochs=50, #params.=63M, FLOPs=293G, fps=7.22023.03 | 52.9 | — | — | 58.7 | — | — | 44 | — | — | — | — | — | — | — | — | — | — | 61.8 | 43 | — | — | — | — | — | — | — | — | — | |
| Lite-ECO-M2FBackbone=SWIN-T, Total GFLOPs=178.43, Encoder GFLOPs=64.422024.04 | 52.84 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=Swin-L*, query type=100 queries, epochs=300, #params=212M, FLOPS=792G, fps=5.22021.12 | 52.7 | — | — | 58.5 | — | — | 44 | — | — | — | — | — | — | — | — | — | 40.1 | 64.8 | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=Swin-L (ImageNet-22K), TTA=false, params=212M2022.06 | 52.7 | — | — | 58.5 | — | — | 44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerBackbone=Swin-L, #Params=212M, #FLOPs=792G, #Queries=100, Epochs=3002022.11 | 52.7 | — | — | 58.5 | — | — | 44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=Swin-L, query type=100 queries, epochs=300, #params.=212M, FLOPs=792G, fps=5.22023.03 | 52.7 | — | — | 58.5 | — | — | 44 | — | — | — | — | — | — | — | — | — | — | 64.8 | 40.1 | — | — | — | — | — | — | — | — | — | |
| Lite-M2FBackbone=SWIN-T, Total GFLOPs=188.00, Encoder GFLOPs=79.782024.04 | 52.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Formerbackbone=R101, query type=100 queries, epochs=50, #params=63M, FLOPS=293G, fps=7.22021.12 | 52.6 | — | — | 58.5 | — | — | 43.7 | — | — | — | — | — | — | — | — | — | 42.6 | 62.4 | — | — | — | — | — | — | — | — | — | — | |
| Mask2Formerbackbone=R101, query type=100 queries, epochs=50, #params.=63M, FLOPs=293G, fps=7.22023.03 | 52.6 | — | — | 58.5 | — | — | 43.7 | — | — | — | — | — | — | — | — | — | — | 62.4 | 42.6 | — | — | — | — | — | — | — | — | — | |
| MP-Formerbackbone=R50, query type=100 queries, epochs=50, #params.=44M, FLOPs=226G, fps=8.62023.03 | 52.2 | — | — | 58.3 | — | — | 42.9 | — | — | — | — | — | — | — | — | — | — | 61.6 | 42.5 | — | — | — | — | — | — | — | — | — | |
| ECO-M2F (β = 0.0005)Backbone=SWIN-T, Total GFLOPs=202.39, Encoder GFLOPs=88.472024.04 | 52.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| M2FBackbone=SWIN-T, Total GFLOPs=235.57, Encoder GFLOPs=121.692024.04 | 52.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Formerbackbone=R50, query type=100 queries, epochs=50, #params=44M, FLOPS=226G, fps=8.62021.12 | 51.9 | — | — | 57.7 | — | — | 43 | — | — | — | — | — | — | — | — | — | 41.7 | 61.7 | — | — | — | — | — | — | — | — | — | — | |
| CleanBackbone=ResNet502024.10 | 51.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 41.7 | 61.7 | — | — | — | — | — | — | — | — | — | — | |
| ECO-M2FBackbone=Res50, Total GFLOPs=195.55, Encoder GFLOPs=92.372024.04 | 51.89 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=Swin-B (ImageNet-22K), TTA=false, params=102M2022.06 | 51.8 | — | — | 56.9 | — | — | 44.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| M2FBackbone=Res50, Total GFLOPs=229.10, Encoder GFLOPs=135.002024.04 | 51.73 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2Formerbackbone=R50, query type=100 queries, epochs=50, #params.=44M, FLOPs=226G, fps=8.62023.03 | 51.4 | — | — | 57.2 | — | — | 42.7 | — | — | — | — | — | — | — | — | — | — | 61.5 | 41.9 | — | — | — | — | — | — | — | — | — | |
| Mask DINO w/ Mr. DETR++Backbone=ResNet-50, Epochs=12, Queries=3002024.12 | 51.2 | — | — | 57.5 | — | — | 41.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 46 | |
| Max-DeepLabbackbone=Max-L, query type=128 queries, epochs=216, #params=451M, FLOPS=3692G2021.12 | 51.1 | — | — | 57 | — | — | 42.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaX-DeepLab-Lbackbone=MaX-L, TTA=false, params=451M2022.06 | 51.1 | — | — | 57 | — | — | 42.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Max-DeepLabbackbone=Max-L, query type=128 queries, epochs=216, #params.=451M, FLOPs=3692G2023.03 | 51.1 | — | — | 57 | — | — | 42.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ECO-M2F (β = 0.02)Backbone=SWIN-T, Total GFLOPs=181.64, Encoder GFLOPs=67.712024.04 | 50.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask DINO w/ Mr. DETRBackbone=ResNet-50, Epochs=12, Queries=3002024.12 | 50.2 | — | — | 56.6 | — | — | 40.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 45.4 | |
| K-NetBackbone=R101-FPN, Box-free=true, NMS-free=true, Epochs=362021.06 | 49.6 | — | — | 55.1 | — | — | 41.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask DINOBackbone=ResNet-50, Epochs=12, Queries=3002024.12 | 49 | — | — | 54.8 | — | — | 40.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 43.2 | |
| MaX-DeepLab-Sbackbone=MaX-S, TTA=false, params=61.9M2022.06 | 48.4 | — | — | 53 | — | — | 41.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| YOSOBackbone=Res50, Total GFLOPs=114.502024.04 | 48.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-NetBackbone=R101-FPN-DCN, Box-free=true, NMS-free=true, Epochs=362021.06 | 48.3 | — | — | 54 | — | — | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Panoptic SegformerBackbone=ResNet-50, Epochs=12, Queries=3532024.12 | 48 | — | — | 52.3 | — | — | 41.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=R101, query type=100 queries, epochs=300, #params=64M, FLOPS=248G, fps=142021.12 | 47.6 | — | — | 52.5 | — | — | 40.3 | — | — | — | — | — | — | — | — | — | 34.1 | 59.3 | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=R101, query type=100 queries, epochs=300, #params.=64M, FLOPs=248G, fps=142023.03 | 47.6 | — | — | 52.5 | — | — | 40.3 | — | — | — | — | — | — | — | — | — | — | 59.3 | 34.1 | — | — | — | — | — | — | — | — | — | |
| K-NetBackbone=R50-FPN, Box-free=true, NMS-free=true, Epochs=362021.06 | 47.1 | — | — | 51.7 | — | — | 40.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mask2FormerBackbone=ResNet-50, Epochs=12, Queries=1002024.12 | 46.9 | — | — | 52.5 | — | — | 38.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RAP-SAMBackbone=Res50, Total GFLOPs=123.002024.04 | 46.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=R50, query type=100 queries, epochs=300, #params=45M, FLOPS=181G, fps=17.62021.12 | 46.5 | — | — | 51 | — | — | 39.8 | — | — | — | — | — | — | — | — | — | 33 | 57.8 | — | — | — | — | — | — | — | — | — | — | |
| MaskFormerbackbone=R50, query type=100 queries, epochs=300, #params.=45M, FLOPs=181G, fps=17.62023.03 | 46.5 | — | — | 51 | — | — | 39.8 | — | — | — | — | — | — | — | — | — | — | 57.8 | 33 | — | — | — | — | — | — | — | — | — | |
| MFBackbone=Res50, Total GFLOPs=181.002024.04 | 46.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PEMBackbone=Res50, Total GFLOPs=110.902024.04 | 46.38 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UViMBackbone=ViT-L/16 (Encoder), ViT-B (Decoder), Pre-training=ImageNet-21k, Input Resolution=1280x12802022.05 | 45.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UVIMmodel category=specialist model, venue=NeurIPS'222023.04 | 45.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DETR-R101Backbone=R1012020.05 | 45.1 | 79.9 | 55.5 | 50.5 | 80.9 | 61.7 | 37 | 78.5 | 46 | 33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DETRbackbone=R101, query type=100 queries, epochs=500+252021.12 | 45.1 | — | — | 50.5 | — | — | 37 | — | — | — | — | — | — | — | — | — | 33 | — | — | — | — | — | — | — | — | — | — | — | |
| DETRbackbone=R101, TTA=false, params=61.8M2022.06 | 45.1 | — | — | 50.5 | — | — | 37 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DETR-R101Backbone=ResNet-1012022.05 | 45.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DETRbackbone=R101, query type=100 queries, epochs=500+252023.03 | 45.1 | — | — | 50.5 | — | — | 37 | — | — | — | — | — | — | — | — | — | — | — | 33 | — | — | — | — | — | — | — | — | — | |
| DETR-DC5Backbone=R50, Dilated C5 (DC5)=true2020.05 | 44.6 | 79.8 | 55 | 49.4 | 80.5 | 60.6 | 37.3 | 78.7 | 46.5 | 31.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BlendMaskBackbone=R-1012020.01 | 44.3 | 80.1 | 53.4 | 51.6 | — | — | 33.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PanopticFPN++Backbone=R101, Schedule=18x2020.05 | 44.1 | 79.5 | 53.3 | 51 | 83.2 | 60.6 | 33.6 | 74 | 42.1 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Axial-DeepLab-Lbackbone=AX-L, TTA=true, params=44.9M2022.06 | 43.9 | — | — | 48.6 | — | — | 36.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Panoptic FCNBackbone=R50-FPN, Box-free=true, NMS-free=true, Epochs=362021.06 | 43.6 | — | — | 49.3 | — | — | 35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DETRBackbone=R502020.05 | 43.4 | 79.3 | 53.8 | 48.2 | 79.8 | 59.5 | 36.3 | 78.5 | 45.3 | 31.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DETRBackbone=R50, Box-free=true, NMS-free=true, Epochs=300+252021.06 | 43.4 | — | — | 48.2 | — | — | 36.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |