Fine Grained Image Classification On Stanford 1

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称	Accuracy	Paper Title	Repository
EfficientNet-B0 (BSConv-S)	61.2%	Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets
ResNet-50	86.31%	PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans
µ2Net+ (ViT-L/16)	93.5%	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
TransFG	92.3% (90.6%)	TransFG: A Transformer Architecture for Fine-grained Recognition
ViT-B/16 (RPE w/ GAB)	90.185%	Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
IELT	91.8%	Fine-Grained Visual Classification via Internal Ensemble Learning Transformer
SIM-OFE	93.3%	SIM-OFE: Structure Information Mining and Object-aware Feature Enhancement for Fine-Grained Visual Categorization	-
WS_DAN-SAC	93.1%	Fine-Grained Visual Classification using Self Assessment Classifier
ViT-NeT (DeiT-III-B)	93.6%	ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder
DB	87.7%	Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes	-
API-Net	90.3%	Learning Attentive Pairwise Interaction for Fine-Grained Classification
MPSA	95.4%	Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification
SEB+EfficientNet-B5	93.0%	On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
RAMS-Trans	92.4%	RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition	-
AFTrans	91.6%	A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition	-
PC-DenseNet-161	83.75%	Pairwise Confusion for Fine-Grained Visual Classification
ImageNet + iNat on WS-DAN	90%	Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization	-
FFVT	91.5%	Feature Fusion Vision Transformer for Fine-Grained Visual Categorization
FAL-ViT	91.1%	An Attention-Locating Algorithm for Eliminating Background Effects in Fine-grained Visual Classification
TPSKG	92.5%	Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition	-

0 of 23 row(s) selected.