Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Fine Grained Image Classification On Oxford 1

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
OmniVec2	99.6	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning	-
ALIGN	96.19%	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
AutoAugment	88.98%	AutoAugment: Learning Augmentation Policies from Data
TNT-B	95.0%	Transformer in Transformer
Bamboo (ViT-B/16)	95.1%	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
DINOv2 (ViT-g/14, frozen model, linear eval)	96.7	DINOv2: Learning Robust Visual Features without Supervision
EfficientNet-B7	95.4%	EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
OmniVec	99.2	OmniVec: Learning robust representations with cross modal sharing	-
AutoFormer-S \| 384	94.9%	AutoFormer: Searching Transformers for Visual Recognition
NAT-M1	-	Neural Architecture Transfer
ViT R26 + S/32 ( Augmented)	96.28	Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection
FixSENet-154	94.8%	Fixing the train-test resolution discrepancy
SEER (RegNet10B)	85.3%	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
IELT	95.28%	Fine-Grained Visual Classification via Internal Ensemble Learning Transformer

0 of 14 row(s) selected.