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/PanopticFPN++

PanopticFPN++

Reported on 30 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Medical10 results

Semantic SegmentationonCOCO minival
AP· 2020-05-26
39.7
best: 53.2 (OpenSeeD (SwinL, single-scale))
SOTA
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
SQth· 2020-05-26
83.2
best: 84.6 (Panoptic FCN* (Swin-L, single-scale))
SOTA
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
PQ· 2020-05-26
44.1
best: 61.2 (HyperSeg (Swin-B))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
PQst· 2020-05-26
33.6
best: 49.2 (OneFormer (InternImage-H,single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
PQth· 2020-05-26
51
best: 67.1 (OneFormer (InternImage-H,single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
RQ· 2020-05-26
53.3
best: 63.5 (MaskFormer (single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
RQst· 2020-05-26
42.1
best: 51.1 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
RQth· 2020-05-26
60.6
best: 68.6 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
SQ· 2020-05-26
79.5
best: 83.2 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Semantic SegmentationonCOCO minival
SQst· 2020-05-26
74
best: 81.1 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872

Audio10 results

10-shot image generationonCOCO minival
AP· 2020-05-26
39.7
best: 53.2 (OpenSeeD (SwinL, single-scale))
SOTA
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
SQth· 2020-05-26
83.2
best: 84.6 (Panoptic FCN* (Swin-L, single-scale))
SOTA
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
PQ· 2020-05-26
44.1
best: 61.2 (HyperSeg (Swin-B))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
PQst· 2020-05-26
33.6
best: 49.2 (OneFormer (InternImage-H,single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
PQth· 2020-05-26
51
best: 67.1 (OneFormer (InternImage-H,single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
RQ· 2020-05-26
53.3
best: 63.5 (MaskFormer (single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
RQst· 2020-05-26
42.1
best: 51.1 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
RQth· 2020-05-26
60.6
best: 68.6 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
SQ· 2020-05-26
79.5
best: 83.2 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
10-shot image generationonCOCO minival
SQst· 2020-05-26
74
best: 81.1 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872

Computer Vision10 results

Panoptic SegmentationonCOCO minival
AP· 2020-05-26
39.7
best: 53.2 (OpenSeeD (SwinL, single-scale))
SOTA
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
SQth· 2020-05-26
83.2
best: 84.6 (Panoptic FCN* (Swin-L, single-scale))
SOTA
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
PQ· 2020-05-26
44.1
best: 61.2 (HyperSeg (Swin-B))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
PQst· 2020-05-26
33.6
best: 49.2 (OneFormer (InternImage-H,single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
PQth· 2020-05-26
51
best: 67.1 (OneFormer (InternImage-H,single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
RQ· 2020-05-26
53.3
best: 63.5 (MaskFormer (single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
RQst· 2020-05-26
42.1
best: 51.1 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
RQth· 2020-05-26
60.6
best: 68.6 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
SQ· 2020-05-26
79.5
best: 83.2 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872
Panoptic SegmentationonCOCO minival
SQst· 2020-05-26
74
best: 81.1 (Panoptic FCN* (Swin-L, single-scale))
End-to-End Object Detection with Transformers arXiv:2005.12872