tieredImageNet

Introduced by Ren et al. in Meta-Learning for Semi-Supervised Few-Shot Classification

The tieredImageNet dataset is a larger subset of ILSVRC-12 with 608 classes (779,165 images) grouped into 34 higher-level nodes in the ImageNet human-curated hierarchy. This set of nodes is partitioned into 20, 6, and 8 disjoint sets of training, validation, and testing nodes, and the corresponding classes form the respective meta-sets. As argued in Ren et al. (2018), this split near the root of the ImageNet hierarchy results in a more challenging, yet realistic regime with test classes that are less similar to training classes.

Source: tieredImageNet

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Few-Shot Image Classification	Tiered ImageNet 5-way (5-shot)	CAML [Laion-2b]
Few-Shot Image Classification	Tiered ImageNet 5-way (1-shot)	CAML [Laion-2b]
Few-Shot Image Classification	Tiered ImageNet 10-way (1-shot)	Transductive CNAPS + FETI
Few-Shot Image Classification	Tiered ImageNet 10-way (5-shot)	Transductive CNAPS + FETI
Unsupervised Few-Shot Image Classification	Tiered ImageNet 5-way (5-shot)	BECLR
Unsupervised Few-Shot Image Classification	Tiered ImageNet 5-way (1-shot)	BECLR
Image Classification	Tiered ImageNet 5-way (5-shot)	EGNN+Transduction