Fine Grained Image Classification On Fgvc

Metrics

Accuracy

FLOPS

PARAMS

Results

Performance results of various models on this benchmark

Model Name	Accuracy	FLOPS	PARAMS	Paper Title	Repository
NAT-M2	89.0%	235M	3.4M	Neural Architecture Transfer
WS-DAN	93.0%	-	-	See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
PCA	92.8%	-	-	Progressive Co-Attention Network for Fine-grained Visual Classification
PMG	93.4%	-	-	Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
Assemble-ResNet-FGVC-50	92.4	-	-	Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
NAT-M3	90.1%	388M	5.1M	Neural Architecture Transfer
CAL	94.2	-	-	Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
BCN	93.5%	-	-	Fine-Grained Visual Classification with Batch Confusion Norm	-
DenseNet161+MM+FRL	94.0 %	-	-	Learning Class Unique Features in Fine-Grained Visual Classification	-
ACNet	92.4%	-	-	Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Inceptionv4	95.11	-	-	Non-binary deep transfer learning for image classification
MC Loss (B-CNN)	92.9%	-	-	The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
DFB-CNN	92.0%	-	-	Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
Mix+	93.1%	-	-	Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
DCAL	93.3%	-	-	Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification	-
CSQA-Net	94.7%	-	-	Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization	-
SR-GNN	95.4	9.8	30.9	SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization
NNCLR	64.1	-	-	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
ELoPE	93.5%	-	-	ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding
CAP	94.9%	-	34.2	Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

0 of 57 row(s) selected.