Mask2Former (Swin-B)

Reported on 4 benchmarks across 4 tasks · 2 papers · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Panoptic SegmentationonLaRS
PQ· 2023-08-18
41.7
SOTA
LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark arXiv:2308.09618
Instance SegmentationonCityscapes val
mask AP· 2021-12-02
42
best: 49 (ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Masked-attention Mask Transformer for Universal Image Segmentation arXiv:2112.01527

Medical1 result

Semantic SegmentationonLaRS
PQ· 2023-08-18
41.7
SOTA
LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark arXiv:2308.09618

Audio1 result

10-shot image generationonLaRS
PQ· 2023-08-18
41.7
SOTA
LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark arXiv:2308.09618