Small Data
Small Data Image Classification is a crucial task in the field of computer vision, focusing on utilizing a limited number of labeled training samples for image classification. This task aims to improve the model's generalization ability and classification accuracy under small sample conditions through efficient learning algorithms and data augmentation techniques, and it has significant application value, especially in scenarios where the cost of data acquisition is high or strict privacy protection is required.
ciFAIR-10 50 samples per class
ChimeraMix+AutoAugment
CIFAR-10, 100 Labels
CIFAR-10, 1000 Labels
CIFAR-10, 250 Labels
GLICO
CIFAR-10, 500 Labels
CIFAR-100, 1000 Labels
ChimeraMix+AutoAugment
cifar10, 10 labels
VAE
CUB-200-2011, 30 samples per class
GLICO
CUB-200-2011, 5 samples per class
GLICO
DEIC Benchmark
Harmonic Networks
EuroSAT 50 samples per class
ImageNet 50 samples per class
Harmonic Networks