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/E2E

E2E

Reported on 12 benchmarks across 3 tasks · 3 papers · 10 SOTA

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

Methodology6 results

Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy Top-5· 2018-07-25
72.09
best: 88.59 (DyTox)
SOTA
End-to-End Incremental Learning arXiv:1807.09536
Incremental LearningonImageNet - 10 steps
Final Accuracy Top-5· 2018-07-25
52.29
best: 84.49 (DyTox)
SOTA
End-to-End Incremental Learning arXiv:1807.09536
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy Top-5· 2018-07-25
89.92
best: 94.17 (TCIL)
SOTA
End-to-End Incremental Learning arXiv:1807.09536
Incremental LearningonImageNet100 - 10 steps
Final Accuracy Top-5· 2018-07-25
80.29
best: 88.84 (TCIL)
SOTA
End-to-End Incremental Learning arXiv:1807.09536
Incremental LearningonImageNet - 10 steps
# M Params· 2018-07-25
11.68
best: 116.89 (DER w/o Pruning)
End-to-End Incremental Learning arXiv:1807.09536
Incremental LearningonImageNet100 - 10 steps
# M Params· 2018-07-25
11.22
best: 116.54 (TCIL)
End-to-End Incremental Learning arXiv:1807.09536

Computer Vision3 results

Zero-Shot Action RecognitiononUCF101
Top-1 Accuracy· 2020-03-03
48
best: 92.8 (OTI(ViT-L/14))
SOTA
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications arXiv:2003.01455
Zero-Shot Action RecognitiononHMDB51
Top-1 Accuracy· 2020-03-03
32.7
best: 64.7 (MOV (ViT-L/14))
SOTA
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications arXiv:2003.01455
Zero-Shot Action RecognitiononActivityNet
Top-1 Accuracy· 2020-03-03
26.6
best: 86.2 (BIKE)
SOTA
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications arXiv:2003.01455

Natural Language Processing3 results

Entity LinkingonOKE-2016
Micro-F1· 2018-08-23
58.4
best: 59.5 (ReFinED)
SOTA
End-to-End Neural Entity Linking arXiv:1808.07699
Entity LinkingonN3-Reuters-128
Micro-F1· 2018-08-23
54.6
best: 58.1 (ReFinED)
SOTA
End-to-End Neural Entity Linking arXiv:1808.07699
Entity LinkingonOKE-2015
Micro-F1· 2018-08-23
66.9
SOTA
End-to-End Neural Entity Linking arXiv:1808.07699