Fine Grained Image Classification On Nabirds

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
BYOL+CVSA (ResNet-50)	79.64%	Exploring Localization for Self-supervised Fine-grained Contrastive Learning	-
API-Net	88.1%	Learning Attentive Pairwise Interaction for Fine-Grained Classification	-
I2-HOFI	92.12%	Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition
TPSKG	90.1%	Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition	-
PIM	92.8%	A Novel Plug-in Module for Fine-Grained Visual Classification	-
MPSA	92.5%	Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification
HERBS	93.0%	Fine-grained Visual Classification with High-temperature Refinement and Background Suppression	-
TransFG	90.8%	TransFG: A Transformer Architecture for Fine-grained Recognition	-
CGL	91.7%	Universal Fine-grained Visual Categorization by Concept Guided Learning
FVE	90.3%	End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition	-
PAIRS	87.9%	Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition	-
CS-Part	88.5%	Classification-Specific Parts for Improving Fine-Grained Visual Categorization	-
MP-FGVC	91.0%	Delving into Multimodal Prompting for Fine-grained Visual Classification	-
MaxEnt-CNN	83.0%	Maximum-Entropy Fine Grained Classification	-
FixSENet-154	89.2%	Fixing the train-test resolution discrepancy	-
FAL-ViT	91.1%	An Attention-Locating Algorithm for Eliminating Background Effects in Fine-grained Visual Classification
CS-Parts	88.5%	Classification-Specific Parts for Improving Fine-Grained Visual Categorization	-
MetaFormer (MetaFormer-2,384)	93.0%	MetaFormer: A Unified Meta Framework for Fine-Grained Recognition	-
Bilinear-CNN	79.4%	Bilinear CNNs for Fine-grained Visual Recognition	-
PC-DenseNet-161	82.79%	Pairwise Confusion for Fine-Grained Visual Classification	-

0 of 27 row(s) selected.