Improving Few-Shot Visual Classification with Unlabelled Examples

Peyman Bateni, Jarred Barber, Jan-Willem van de Meent, Frank Wood

Keywords: Meta-learning, Few-shot image classification, Transductive few-shot learning

Abstract: We propose a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering procedure with a modified state of the art neural adaptive feature extractor to achieve improved test-time classification accuracy using unlabelled data. We evaluate our method on transductive few-shot learning tasks, in which the goal is to jointly predict labels for query (test) examples given a set of support (training) examples. We achieve new state of the art performance on the Meta-Dataset and the mini-ImageNet and tiered-ImageNet benchmarks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose Transductive CNAPS, a neural adaptive Mahalanobis-distance based soft k-means approach for transductive few-shot image classification.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2006.12245/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=6zw3jKDnih