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/Resnet50

Resnet50

Reported on 28 benchmarks across 16 tasks · 2 papers

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

Computer Vision13 results

3D Human Pose EstimationonH3WB
MPJPE· 2022-11-28
151.6
best: 264.4 (CanonPose)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
HandonH3WB
Average MPJPE (mm)· 2022-11-28
63.1
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
Pose EstimationonH3WB
MPJPE· 2022-11-28
151.6
best: 264.4 (CanonPose)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
Pose EstimationonH3WB
Average MPJPE (mm)· 2022-11-28
63.1
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
Facial Landmark DetectiononH3WB
Average MPJPE (mm)· 2022-11-28
26.3
best: 34 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
Face ReconstructiononH3WB
Average MPJPE (mm)· 2022-11-28
26.3
best: 34 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
3D Face ReconstructiononH3WB
Average MPJPE (mm)· 2022-11-28
26.3
best: 34 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
3D Hand Pose EstimationonH3WB
Average MPJPE (mm)· 2022-11-28
63.1
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
Image ClassificationonRailway Track Misalignment Detection Image Dataset
Batch Size
64
best: 128 (VGG16)
Image ClassificationonRailway Track Misalignment Detection Image Dataset
Classification Accuracy
0.973
best: 0.982 (VGG16)
Image ClassificationonRailway Track Misalignment Detection Image Dataset
Epochs
6
best: 9 (inception)
Image ClassificationonRailway Track Misalignment Detection Image Dataset
Learning Rate
0.0001
Image RecognitiononCUB Birds
1:1 Accuracy
89.6

Audio6 results

10-shot image generationonMapillary val
mIoU· 2023-11-30
32.93
best: 76 (AO-SegNet)
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
10-shot image generationonCityscapes val
mIoU· 2023-11-30
34.66
best: 90.3 (EfficientPS (Cityscapes-fine))
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
10-shot image generationonBDD100K val
mIoU· 2023-11-30
31.44
best: 72.5 (VLTSeg)
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
10-shot image generationonSYNTHIA
mIoU· 2023-11-30
25.84
best: 83.8 (CGA-Net)
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
1 Image, 2*2 StitchionH3WB
MPJPE· 2022-11-28
151.6
best: 264.4 (CanonPose)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
1 Image, 2*2 StitchionH3WB
Average MPJPE (mm)· 2022-11-28
63.1
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692

Medical5 results

Semantic SegmentationonMapillary val
mIoU· 2023-11-30
32.93
best: 76 (AO-SegNet)
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
Semantic SegmentationonCityscapes val
mIoU· 2023-11-30
34.66
best: 90.3 (EfficientPS (Cityscapes-fine))
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
Semantic SegmentationonBDD100K val
mIoU· 2023-11-30
31.44
best: 72.5 (VLTSeg)
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
Semantic SegmentationonSYNTHIA
mIoU· 2023-11-30
25.84
best: 83.8 (CGA-Net)
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation arXiv:2311.18331
3D Face ModellingonH3WB
Average MPJPE (mm)· 2022-11-28
26.3
best: 34 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692

Methodology3 results

3DonH3WB
MPJPE· 2022-11-28
151.6
best: 264.4 (CanonPose)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
3DonH3WB
Average MPJPE (mm)· 2022-11-28
63.1
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692
3DonH3WB
Average MPJPE (mm)· 2022-11-28
26.3
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692

Music1 result

Facial Recognition and ModellingonH3WB
Average MPJPE (mm)· 2022-11-28
26.3
best: 34 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692

Graphs1 result

Hand Pose EstimationonH3WB
Average MPJPE (mm)· 2022-11-28
63.1
best: 83.4 (SimpleBaseline)
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark arXiv:2211.15692