ViT R26 + S/32 ( Augmented)

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

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

Computer Vision2 results

Image ClassificationonOxford-IIIT Pet Dataset
Accuracy· uses extra data· 2021-08-28
96.28
best: 99.6 (OmniVec2)
SOTA
Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection arXiv:2109.00891
Fine-Grained Image ClassificationonOxford-IIIT Pet Dataset
Accuracy· uses extra data· 2021-08-28
96.28
best: 99.6 (OmniVec2)
SOTA
Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection arXiv:2109.00891