Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization

Open paper

Benchmark	Model	Rank	Results
fine-grained-image-classification-on-fgvc	CSQA-Net	–	Accuracy: 94.7%
fine-grained-image-classification-on-nabirds	CSQA-Net	–	Accuracy: 92.3%
fine-grained-image-classification-on-stanford	CSQA-Net	–	Accuracy: 95.6%