Collections:
- Name: Mask2Former
  License: Apache License 2.0
  Metadata:
    Training Data:
    - Usage
    - Cityscapes
    - ADE20K
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  README: configs/mask2former/README.md
  Frameworks:
  - PyTorch
Models:
- Name: mask2former_r50_8xb2-90k_cityscapes-512x1024
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 80.44
  Config: configs/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024.py
  Metadata:
    Training Data: Cityscapes
    Batch Size: 16
    Architecture:
    - R-50-D32
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 5.67
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802-ffd9d750.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-90k_cityscapes-512x1024/mask2former_r50_8xb2-90k_cityscapes-512x1024_20221202_140802.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_r101_8xb2-90k_cityscapes-512x1024
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 80.8
  Config: configs/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024.py
  Metadata:
    Training Data: Cityscapes
    Batch Size: 16
    Architecture:
    - R-101-D32
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 6.81
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628-43e68666.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-90k_cityscapes-512x1024/mask2former_r101_8xb2-90k_cityscapes-512x1024_20221130_031628.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-t_8xb2-90k_cityscapes-512x1024
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 81.71
  Config: configs/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024.py
  Metadata:
    Training Data: Cityscapes
    Batch Size: 16
    Architecture:
    - Swin-T
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 6.36
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501-36c59341.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-90k_cityscapes-512x1024/mask2former_swin-t_8xb2-90k_cityscapes-512x1024_20221127_144501.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-s_8xb2-90k_cityscapes-512x1024
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 82.57
  Config: configs/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024.py
  Metadata:
    Training Data: Cityscapes
    Batch Size: 16
    Architecture:
    - Swin-S
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 8.09
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802-9ab177f6.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-90k_cityscapes-512x1024/mask2former_swin-s_8xb2-90k_cityscapes-512x1024_20221127_143802.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 83.52
  Config: configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py
  Metadata:
    Training Data: Cityscapes
    Batch Size: 16
    Architecture:
    - Swin-B
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 10.89
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030-9a86a225.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-b-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221203_045030.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: Cityscapes
    Metrics:
      mIoU: 83.65
  Config: configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py
  Metadata:
    Training Data: Cityscapes
    Batch Size: 16
    Architecture:
    - Swin-L
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 15.83
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-28ad20f1.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_r50_8xb2-160k_ade20k-512x512
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 47.87
  Config: configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - R-50-D32
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 3.31
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-2d1f55f1.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_r101_8xb2-160k_ade20k-512x512
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 48.6
  Config: configs/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - R-101-D32
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 4.09
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905-b7135890.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_r101_8xb2-160k_ade20k-512x512/mask2former_r101_8xb2-160k_ade20k-512x512_20221203_233905.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-t_8xb2-160k_ade20k-512x512
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 48.66
  Config: configs/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-T
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 3826.0
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230-7d64e5dd.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-t_8xb2-160k_ade20k-512x512/mask2former_swin-t_8xb2-160k_ade20k-512x512_20221203_234230.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-s_8xb2-160k_ade20k-512x512
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 51.24
  Config: configs/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-S
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 3.74
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905-e715144e.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-s_8xb2-160k_ade20k-512x512/mask2former_swin-s_8xb2-160k_ade20k-512x512_20221204_143905.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 52.44
  Config: configs/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-B
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 5.66
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118-a4a086d2.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in1k-384x384-pre_8xb2-160k_ade20k-640x640_20221129_125118.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 53.9
  Config: configs/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-B
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 5.66
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230-7ec0f569.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-b-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235230.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch
- Name: mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640
  In Collection: Mask2Former
  Results:
    Task: Semantic Segmentation
    Dataset: ADE20K
    Metrics:
      mIoU: 56.01
  Config: configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640.py
  Metadata:
    Training Data: ADE20K
    Batch Size: 16
    Architecture:
    - Swin-L
    - Mask2Former
    Training Resources: 8x A100 GPUS
    Memory (GB): 8.86
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933-7120c214.pth
  Training log: https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640/mask2former_swin-l-in22k-384x384-pre_8xb2-160k_ade20k-640x640_20221203_235933.json
  Paper:
    Title: Masked-attention Mask Transformer for Universal Image Segmentation
    URL: https://arxiv.org/abs/2112.01527
  Code: https://github.com/open-mmlab/mmdetection/blob/3.x/mmdet/models/dense_heads/mask2former_head.py
  Framework: PyTorch