Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/K-Net (R101-FPN-DCN)

K-Net (R101-FPN-DCN)

Reported on 9 benchmarks across 3 tasks · 1 paper

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

Medical3 results

Semantic SegmentationonCOCO test-dev
PQ· 2021-06-28
48.3
best: 59.5 (Mask DINO (single scale))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855
Semantic SegmentationonCOCO test-dev
PQst· 2021-06-28
39.7
best: 58.9 (MaskConver (ResNet50, single-scale))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855
Semantic SegmentationonCOCO test-dev
PQth· 2021-06-28
54
best: 65.1 (Mask2Former (Swin-L))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855

Audio3 results

10-shot image generationonCOCO test-dev
PQ· 2021-06-28
48.3
best: 59.5 (Mask DINO (single scale))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855
10-shot image generationonCOCO test-dev
PQst· 2021-06-28
39.7
best: 58.9 (MaskConver (ResNet50, single-scale))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855
10-shot image generationonCOCO test-dev
PQth· 2021-06-28
54
best: 65.1 (Mask2Former (Swin-L))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855

Computer Vision3 results

Panoptic SegmentationonCOCO test-dev
PQ· 2021-06-28
48.3
best: 59.5 (Mask DINO (single scale))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855
Panoptic SegmentationonCOCO test-dev
PQst· 2021-06-28
39.7
best: 58.9 (MaskConver (ResNet50, single-scale))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855
Panoptic SegmentationonCOCO test-dev
PQth· 2021-06-28
54
best: 65.1 (Mask2Former (Swin-L))
K-Net: Towards Unified Image Segmentation arXiv:2106.14855