Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Benchmark Model Rank Results
fine-grained-image-classification-on-food-101CAP#1Accuracy: 98.6PARAMS: 34.2
fine-grained-image-classification-on-cub-200-2011CAP#4Accuracy: 91.8
fine-grained-image-classification-on-fgvc-aircraftCAP#4Accuracy: 94.9%PARAMS: 34.2
fine-grained-image-classification-on-stanford-carsCAP#9Accuracy: 95.7%
fine-grained-image-classification-on-nabirdsCAP#10Accuracy: 91.0%