OpenCodePapers

fine-grained-image-classification-on-oxford-1

Fine-Grained Image Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyTop-1 Error RateFLOPSPARAMSModelNameReleaseDate
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning99.6OmniVec22024-01-01
OmniVec: Learning robust representations with cross modal sharing99.2OmniVec2023-11-07
DINOv2: Learning Robust Visual Features without Supervision✓ Link96.7DINOv2 (ViT-g/14, frozen model, linear eval)2023-04-14
Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection✓ Link96.28ViT R26 + S/32 ( Augmented)2021-08-28
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision✓ Link96.19%ALIGN2021-02-11
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks✓ Link95.4%EfficientNet-B72019-05-28
Fine-Grained Visual Classification via Internal Ensemble Learning Transformer✓ Link95.28%IELT2023-02-13
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy✓ Link95.1%Bamboo (ViT-B/16)2022-03-15
Transformer in Transformer✓ Link95.0%65.6MTNT-B2021-02-27
AutoFormer: Searching Transformers for Visual Recognition✓ Link94.9%AutoFormer-S | 3842021-07-01
Fixing the train-test resolution discrepancy✓ Link94.8%5.2%FixSENet-1542019-06-14
AutoAugment: Learning Augmentation Policies from Data✓ Link88.98%11.02%AutoAugment2018-05-24
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics✓ Link88.31MANO-tiny2025-07-03
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision✓ Link85.3%SEER (RegNet10B)2022-02-16
Neural Architecture Transfer✓ Link160M4.0MNAT-M12020-05-12
Check out how to contribute new results.