CIFAR-FS

CIFAR100 few-shots

ImagesUnknownIntroduced 2018-05-21

CIFAR100 few-shots (CIFAR-FS) is randomly sampled from CIFAR-100 (Krizhevsky & Hinton, 2009) by using the same criteria with which miniImageNet has been generated. The average inter-class similarity is sufficiently high to represent a challenge for the current state of the art. Moreover, the limited original resolution of 32×32 makes the task harder and at the same time allows fast prototyping.

Source: Bertinetto et al. Image source: Bertinetto et al.

Related Benchmarks

CIFAR-FS - 1-Shot Learning/Few-Shot Image Classification/Accuracy CIFAR-FS - 1-Shot Learning/Image Classification/Accuracy CIFAR-FS - 5-Shot Learning/Few-Shot Image Classification/Accuracy CIFAR-FS - 5-Shot Learning/Image Classification/Accuracy CIFAR-FS 5-way (1-shot)/Few-Shot Image Classification/Accuracy CIFAR-FS 5-way (1-shot)/Image Classification/Accuracy CIFAR-FS 5-way (5-shot)/Few-Shot Image Classification/Accuracy CIFAR-FS 5-way (5-shot)/Image Classification/Accuracy