Few-Shot Learning2016

miniImageNet Few-Shot Classification (5-way 5-shot)

Canonical few-shot image classification benchmark. 100 classes drawn from ImageNet (64 train / 16 val / 20 test). Evaluation episodes sample 5 novel classes with 5 support examples each and query images to classify.

No benchmark results indexed for this dataset yet.

Contribute results on GitHub
miniImageNet 5-way 5-shot Benchmark - Few-Shot Learning | CodeSOTA