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/SEED

SEED

Reported on 16 benchmarks across 6 tasks · 2 papers · 9 SOTA

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

Methodology7 results

Continual LearningonCifar100-B0(10 tasks)-no-exemplars
Average Incremental Accuracy· 2024-01-18
61.7
SOTA
Divide and not forget: Ensemble of selectively trained experts in Continual Learning arXiv:2401.10191
Continual LearningonCIFAR100-B0(50 tasks)-no-exemplars
Average Incremental Accuracy· 2024-01-18
42.6
SOTA
Divide and not forget: Ensemble of selectively trained experts in Continual Learning arXiv:2401.10191
Continual LearningonCifar100-B0(20 tasks)-no-exemplars
Average Incremental Accuracy· 2024-01-18
56.2
SOTA
Divide and not forget: Ensemble of selectively trained experts in Continual Learning arXiv:2401.10191
Class Incremental LearningonCifar100-B0(10 tasks)-no-exemplars
Average Incremental Accuracy· 2024-01-18
61.7
SOTA
Divide and not forget: Ensemble of selectively trained experts in Continual Learning arXiv:2401.10191
Class Incremental LearningonCIFAR100-B0(50 tasks)-no-exemplars
Average Incremental Accuracy· 2024-01-18
42.6
SOTA
Divide and not forget: Ensemble of selectively trained experts in Continual Learning arXiv:2401.10191
Class Incremental LearningonCifar100-B0(20 tasks)-no-exemplars
Average Incremental Accuracy· 2024-01-18
56.2
SOTA
Divide and not forget: Ensemble of selectively trained experts in Continual Learning arXiv:2401.10191
Optical Character Recognition (OCR)onBenchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
Accuracy (%)· 2020-05-22
61.2
best: 89.6 (DTrOCR)
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977

Computer Vision6 results

Scene ParsingonICDAR2015
Accuracy· 2020-05-22
80
best: 93.5 (DTrOCR 105M)
SOTA
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
Scene Text RecognitiononICDAR2015
Accuracy· 2020-05-22
80
best: 93.5 (DTrOCR 105M)
SOTA
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
Scene ParsingonSVT
Accuracy· 2020-05-22
89.6
best: 99.1 (CLIP4STR-H (DFN-5B))
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
Scene ParsingonICDAR2013
Accuracy· 2020-05-22
92.8
best: 99.42 (CLIP4STR-L*)
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
Scene Text RecognitiononSVT
Accuracy· 2020-05-22
89.6
best: 99.1 (CLIP4STR-H (DFN-5B))
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
Scene Text RecognitiononICDAR2013
Accuracy· 2020-05-22
92.8
best: 99.42 (CLIP4STR-L*)
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977

Audio3 results

2D Semantic SegmentationonICDAR2015
Accuracy· 2020-05-22
80
best: 93.5 (DTrOCR 105M)
SOTA
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
2D Semantic SegmentationonSVT
Accuracy· 2020-05-22
89.6
best: 99.1 (CLIP4STR-H (DFN-5B))
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977
2D Semantic SegmentationonICDAR2013
Accuracy· 2020-05-22
92.8
best: 99.42 (CLIP4STR-L*)
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition arXiv:2005.10977