FC100

Fewshot-CIFAR100

The FC100 dataset (Fewshot-CIFAR100) is a newly split dataset based on CIFAR-100 for few-shot learning. It contains 20 high-level categories which are divided into 12, 4, 4 categories for training, validation and test. There are 60, 20, 20 low-level classes in the corresponding split containing 600 images of size 32 × 32 per class. Smaller image size makes it more challenging for few-shot learning. Source: Prototype Rectification for Few-Shot Learning

Images

벤치마크

Few-Shot Image Classification on FC100 5-way (1-shot) 결과 44개

Few-Shot Image Classification on FC100 5-way (5-shot) 결과 44개

Few-Shot Image Classification on FC100 5-way (10-shot) 결과 2개

Few-Shot Image Classification on Fewshot-CIFAR100 - 1-Shot Learning 결과 2개

Few-Shot Image Classification on Fewshot-CIFAR100 - 5-Shot Learning 결과 2개