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/OCR (HRNetV2-W48)

OCR (HRNetV2-W48)

Reported on 8 benchmarks across 2 tasks · 2 papers · 4 SOTA

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

Medical4 results

Semantic SegmentationonUrbanLF
mIoU (Real)· 2015-05-18
78.6
best: 83.22 (CMNeXt (RGB-LF8))
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Semantic SegmentationonUrbanLF
mIoU (Syn)· 2015-05-18
79.36
best: 81.02 (CMNeXt (RGB-LF80))
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Semantic SegmentationonADE20K val
mIoU· 2019-09-24
45.66
best: 62.8 (BEiT-3)
Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation arXiv:1909.11065
Semantic SegmentationonPASCAL Context
mIoU· 2019-09-24
56.2
best: 71.1 (VPNeXt)
Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation arXiv:1909.11065

Audio4 results

10-shot image generationonUrbanLF
mIoU (Real)· 2015-05-18
78.6
best: 83.22 (CMNeXt (RGB-LF8))
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
10-shot image generationonUrbanLF
mIoU (Syn)· 2015-05-18
79.36
best: 81.02 (CMNeXt (RGB-LF80))
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
10-shot image generationonADE20K val
mIoU· 2019-09-24
45.66
best: 62.8 (BEiT-3)
Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation arXiv:1909.11065
10-shot image generationonPASCAL Context
mIoU· 2019-09-24
56.2
best: 71.1 (VPNeXt)
Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation arXiv:1909.11065