mini-Imagenet

Introduced by Vinyals et al. in Matching Networks for One Shot Learning

mini-Imagenet is proposed by Matching Networks for One Shot Learning . In NeurIPS, 2016. This dataset consists of 50000 training images and 10000 testing images, evenly distributed across 100 classes.

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Few-Shot Image Classification	Mini-Imagenet 5-way (1-shot)	CAML [Laion-2b]
Few-Shot Image Classification	Mini-Imagenet 5-way (5-shot)	CAML [Laion-2b]
Unsupervised Few-Shot Image Classification	Mini-Imagenet 5-way (1-shot)	BECLR
Unsupervised Few-Shot Image Classification	Mini-Imagenet 5-way (5-shot)	BECLR
Few-Shot Image Classification	Mini-ImageNet - 1-Shot Learning	EPNet
Few-Shot Image Classification	Mini-Imagenet 10-way (5-shot)	Transductive CNAPS + FETI
Few-Shot Image Classification	Mini-Imagenet 10-way (1-shot)	Transductive CNAPS + FETI
Few-Shot Image Classification	Mini-ImageNet-CUB 5-way (1-shot)	TRIDENT
Few-Shot Class-Incremental Learning	mini-Imagenet	SV-T
Few-Shot Image Classification	Mini-ImageNet-CUB 5-way (5-shot)	TRIDENT
Few-Shot Image Classification	Mini-Imagenet 20-way (5-shot)	Meta LSTM,
Few-Shot Image Classification	Mini-Imagenet 20-way (1-shot)	TIM-GD
Few-Shot Image Classification	Mini-Imagenet 5-way (10-shot)	PT+MAP
Few-Shot Learning	Mini-Imagenet 5-way (1-shot)	EASY
Few-Shot Learning	Mini-ImageNet - 5-Shot Learning	TIM-GD
Few-Shot Image Classification	Mini-ImageNet to CUB - 5 shot learning	TIM-GD
Few-Shot Learning	Mini-ImageNet - 1-Shot Learning	DPGN
Cross-Domain Few-Shot	miniImagenet	Domain Agnostic Meta Score-based Learning
Few-Shot Image Classification	mini-ImageNet - 100-Way	GCR