Collections: - Name: Mask2Former Metadata: Training Techniques: - AdamW - Weight Decay Training Resources: 8x A100 GPUs Architecture: - Mask2Former Paper: URL: https://arxiv.org/pdf/2112.10764.pdf Title: Mask2Former for Video Instance Segmentation README: configs/mask2former/README.md Models: - Name: mask2former_r50_8xb2-8e_youtubevis2021 In Collection: Mask2Former Config: configs/mask2former_vis/mask2former_r50_8xb2-8e_youtubevis2021.py Metadata: Training Data: YouTube-VIS 2021 Training Memory (GB): 6.0 Results: - Task: Video Instance Segmentation Dataset: YouTube-VIS 2021 Metrics: AP: 41.3 Weights: https://download.openmmlab.com/mmdetection/v3.0/mask2former_vis/mask2former_r50_8xb2-8e_youtubevis2021/mask2former_r50_8xb2-8e_youtubevis2021_20230426_131833-5d215283.pth - Name: mask2former_r101_8xb2-8e_youtubevis2021 In Collection: Mask2Former Config: configs/mask2former_vis/mask2former_r101_8xb2-8e_youtubevis2021.py Metadata: Training Data: YouTube-VIS 2021 Training Memory (GB): 7.5 Results: - Task: Video Instance Segmentation Dataset: YouTube-VIS 2021 Metrics: AP: 42.3 Weights: https://download.openmmlab.com/mmdetection/v3.0/mask2former_vis/mask2former_r101_8xb2-8e_youtubevis2021/mask2former_r101_8xb2-8e_youtubevis2021_20220823_092747-8077d115.pth - Name: mask2former_swin-l-p4-w12-384-in21k_8xb2-8e_youtubevis2021.py In Collection: Mask2Former Config: configs/mask2former_vis/mask2former_swin-l-p4-w12-384-in21k_8xb2-8e_youtubevis2021.py Metadata: Training Data: YouTube-VIS 2021 Training Memory (GB): 18.5 Results: - Task: Video Instance Segmentation Dataset: YouTube-VIS 2021 Metrics: AP: 52.3 Weights: https://download.openmmlab.com/mmdetection/v3.0/mask2former_vis/mask2former_swin-l-p4-w12-384-in21k_8xb2-8e_youtubevis2021/mask2former_swin-l-p4-w12-384-in21k_8xb2-8e_youtubevis2021_20220907_124752-48252603.pth