Fine Grained Image Classification On Stanford

评估指标

Accuracy

PARAMS

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
TResnet-L + PMD	97.3%	-	Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition
CMAL-Net	97.1%	-	Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual Classification	-
I2-HOFI	96.92%	-	Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition	-
TResNet-L + ML-Decoder	96.41%	-	ML-Decoder: Scalable and Versatile Classification Head
DAT	96.2%	-	Domain Adaptive Transfer Learning with Specialist Models	-
ALIGN	96.13%	-	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
SR-GNN	96.1	30.9	SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization
EffNet-L2 (SAM)	95.96%	-	Sharpness-Aware Minimization for Efficiently Improving Generalization
SaSPA + CAL	95.72	-	Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
CAP	95.7%	-	Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
CSQA-Net	95.6%	-	Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization	-
AttNet & AffNet	95.6%	-	Fine-Grained Visual Classification with Efficient End-to-end Localization	-
CCFR	95.5%	-	Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition	-
CAL	95.5%	-	Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
MPSA	95.4%	-	Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification	-
Inceptionv4	95.35%	-	Non-binary deep transfer learning for image classification
DCAL	95.3%	-	Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification	-
API-Net	95.3%	-	Learning Attentive Pairwise Interaction for Fine-Grained Classification
PART	95.3%	-	Part-guided Relational Transformers for Fine-grained Visual Recognition
DenseNet161+MM+FRL	95.2%	-	Learning Class Unique Features in Fine-Grained Visual Classification	-

0 of 82 row(s) selected.