Fine-Grained Image Classification on Oxford-IIIT Pet Dataset

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	OmniVec2	99.6	Yes	-	-	-
2	OmniVec	99.2	Yes	OmniVec: Learning robust representations with cr...	2023-11-07	-
3	DINOv2 (ViT-g/14, frozen model, linear eval)	96.7	Yes	DINOv2: Learning Robust Visual Features without ...	2023-04-14	Code
4	ViT R26 + S/32 ( Augmented)	96.28	Yes	Towards Fine-grained Image Classification with G...	2021-08-28	Code
5	MANO-tiny	88.31	Yes	Linear Attention with Global Context: A Multipol...	2025-07-03	Code

#1OmniVec2
99.6
Accuracy· Extra Data
No paper
#2OmniVecSOTA
99.2
Accuracy· Extra Data· 2023-11-07
OmniVec: Learning robust representations with cross modal sharing
#3DINOv2 (ViT-g/14, frozen model, linear eval)SOTA
96.7
Accuracy· Extra Data· 2023-04-14
DINOv2: Learning Robust Visual Features without Supervision Code
#4ViT R26 + S/32 ( Augmented)SOTA
96.28
Accuracy· Extra Data· 2021-08-28
Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection Code
#5MANO-tiny
88.31
Accuracy· Extra Data· 2025-07-03
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics Code