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/DeiT-B

DeiT-B

Reported on 12 benchmarks across 4 tasks · 3 papers · 5 SOTA

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

Computer Vision10 results

Document Layout AnalysisonPubLayNet val
Figure· 2020-12-23
0.957
best: 0.975 (DETR)
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Document Layout AnalysisonPubLayNet val
List· 2020-12-23
0.921
best: 0.975 (TRDLU)
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Document Layout AnalysisonPubLayNet val
Overall· 2020-12-23
0.932
best: 0.962 (VGT)
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Document Layout AnalysisonPubLayNet val
Text· 2020-12-23
0.934
best: 0.967 (VSR)
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Document Layout AnalysisonPubLayNet val
Title· 2020-12-23
0.874
best: 0.939 (VGT)
SOTA
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Image ClassificationonImageNet
GFLOPs· 2024-09-16
16.87
best: 1478 (InternImage-H)
Kolmogorov-Arnold Transformer arXiv:2409.10594
Image ClassificationonImageNet
Top 1 Accuracy· 2024-09-16
81.8
best: 88.3 (Unicom (ViT-L/14@336px) (Finetuned))
Kolmogorov-Arnold Transformer arXiv:2409.10594
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2020-12-23
99.1
best: 99.5 (ViT-H/14)
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2020-12-23
90.8
best: 96.08 (EffNet-L2 (SAM))
Training data-efficient image transformers & distillation through attention arXiv:2012.12877
Document Layout AnalysisonPubLayNet val
Table· 2020-12-23
0.972
best: 0.981 (VGT)
Training data-efficient image transformers & distillation through attention arXiv:2012.12877

Medical1 result

Semantic SegmentationonADE20K val
mIoU· 2022-04-14
54.1
best: 62.8 (BEiT-3)
DeiT III: Revenge of the ViT arXiv:2204.07118

Audio1 result

10-shot image generationonADE20K val
mIoU· 2022-04-14
54.1
best: 62.8 (BEiT-3)
DeiT III: Revenge of the ViT arXiv:2204.07118