ImageNet + iNat on WS-DAN

Reported on 5 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Computer Vision5 results

Image ClassificationonStanford Cars
Accuracy· 2020-10-06
94.1
best: 96.868 (efficient adaptive ensembling)
SOTA
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization arXiv:2010.03071
Image ClassificationonFGVC Aircraft
Top-1· 2020-10-06
91.5
SOTA
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization arXiv:2010.03071
Fine-Grained Image ClassificationonFGVC Aircraft
Top-1· 2020-10-06
91.5
SOTA
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization arXiv:2010.03071
Image ClassificationonFood-101
Top 1 Accuracy· 2020-10-06
88.7
best: 92.47 (Assemble-ResNet-FGVC-50)
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization arXiv:2010.03071
Fine-Grained Image ClassificationonFood-101
Top 1 Accuracy· 2020-10-06
88.7
best: 92.47 (Assemble-ResNet-FGVC-50)
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization arXiv:2010.03071