Fine Grained Image Classification On Cub 200 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
TBMSL-Net	89.6	Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization
FBSD	89.5	Feature Boosting, Suppression, and Diversification for Fine-Grained Visual Classification
MPN-COV	88.7	Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
SWAG (ViT H/14)	91.7	Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Nts-Net	87.5	Are These Birds Similar: Learning Branched Networks for Fine-grained Representations
MACNN	86.5	Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition
DFL-CNN	87.4	Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
PC	86.9	Pairwise Confusion for Fine-Grained Visual Classification
TASN	87.9	Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition
BYOL+CVSA (ResNet-50)	77.1	Exploring Localization for Self-supervised Fine-grained Contrastive Learning
CAP	91.8	Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
DenseNet161+MM+FRL	88.5	Learning Class Unique Features in Fine-Grained Visual Classification	-
DATL	91.2	Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization	-
LIO	88.0	Look-into-Object: Self-supervised Structure Modeling for Object Recognition
CAL	90.6	Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
ResNet-50	88.59	PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans
Basel.+LSRO	84.4	Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
FFVT	91.6	Feature Fusion Vision Transformer for Fine-Grained Visual Categorization
WS-DAN	89.4	See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
HOI-Net	90.02%	High-Order-Interaction for weakly supervised Fine-Grained Visual Categorization

0 of 26 row(s) selected.