Fine Grained Image Classification On Cub 200

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
MP-FGVC	91.8%	Delving into Multimodal Prompting for Fine-grained Visual Classification	-
Stacked LSTM	90.4%	Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
GCL	88.3%	Graph-propagation based Correlation Learning for Weakly Supervised Fine-grained Image Classification	-
MGE-CNN	89.4%	Learning a Mixture of Granularity-Specific Experts for Fine-Grained Categorization
DFB	87.4%	Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
BCN	89.2%	Fine-Grained Visual Classification with Batch Confusion Norm	-
MHEM (a strong ResNet50 baseline)	88.2%	Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification
Mix+	90.2%	Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
TransIFC	91.0%	TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification	-
CAP	91.8%	Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
Correspondence with Convolutional Hough Matching Networks	83.27	Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
SnapMix	89.58%	SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
SIM-Trans	91.8%	SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization
API-Net	90.0%	Learning Attentive Pairwise Interaction for Fine-Grained Classification
TransFG	91.7%	TransFG: A Transformer Architecture for Fine-grained Recognition
Correspondence with Earth mover's distance	84.98	Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
SEF	87.3%	Learning Semantically Enhanced Feature for Fine-Grained Image Classification
CIN	88.3%	Channel Interaction Networks for Fine-Grained Image Categorization	-
DF-GMM	88.8%	Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning	-
GAT	88.66%	Human Attention in Fine-grained Classification

0 of 73 row(s) selected.