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/DTrOCR 105M

DTrOCR 105M

Reported on 21 benchmarks across 5 tasks · 1 paper · 11 SOTA

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

Computer Vision12 results

Scene ParsingonSVTP
Accuracy· 2023-08-30
98.6
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene ParsingonICDAR2015
Accuracy· 2023-08-30
93.5
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene ParsingonICDAR2013
Accuracy· 2023-08-30
99.4
best: 99.42 (CLIP4STR-L*)
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene Text RecognitiononSVTP
Accuracy· 2023-08-30
98.6
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene Text RecognitiononICDAR2015
Accuracy· 2023-08-30
93.5
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene Text RecognitiononICDAR2013
Accuracy· 2023-08-30
99.4
best: 99.42 (CLIP4STR-L*)
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene ParsingonSVT
Accuracy· 2023-08-30
98.9
best: 99.1 (CLIP4STR-H (DFN-5B))
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene ParsingonCUTE80
Accuracy· 2023-08-30
99.1
best: 99.7 (CPPD)
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene ParsingonIIIT5k
Accuracy· 2023-08-30
99.6
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene Text RecognitiononSVT
Accuracy· 2023-08-30
98.9
best: 99.1 (CLIP4STR-H (DFN-5B))
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene Text RecognitiononCUTE80
Accuracy· 2023-08-30
99.1
best: 99.7 (CPPD)
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Scene Text RecognitiononIIIT5k
Accuracy· 2023-08-30
99.6
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996

Audio6 results

2D Semantic SegmentationonSVTP
Accuracy· 2023-08-30
98.6
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
2D Semantic SegmentationonICDAR2015
Accuracy· 2023-08-30
93.5
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
2D Semantic SegmentationonICDAR2013
Accuracy· 2023-08-30
99.4
best: 99.42 (CLIP4STR-L*)
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
2D Semantic SegmentationonSVT
Accuracy· 2023-08-30
98.9
best: 99.1 (CLIP4STR-H (DFN-5B))
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
2D Semantic SegmentationonCUTE80
Accuracy· 2023-08-30
99.1
best: 99.7 (CPPD)
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
2D Semantic SegmentationonIIIT5k
Accuracy· 2023-08-30
99.6
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996

Methodology2 results

Optical Character Recognition (OCR)onIAM
CER· 2023-08-30
2.38
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996
Optical Character Recognition (OCR)onBenchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
Accuracy (%)· 2023-08-30
89.6
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996

Adversarial1 result

Handwritten Text RecognitiononIAM
CER· 2023-08-30
2.38
SOTA
DTrOCR: Decoder-only Transformer for Optical Character Recognition arXiv:2308.15996