Meta-learning for semi-supervised few-shot classification
Name
1803.00676.pdf
Description
Accepted version
Size
1.93 MB
Format
Adobe PDF
Checksum (MD5)
7a01d5c973f01ad350103e67d5e7b2cd
Author(s)
Tenenbaum, Joshua B
Date Issued
April 2018
Journal
ICLR 2018
Publisher
ICLR
Citation
Ren, Mengye et al. “Meta-learning for semi-supervised few-shot classification.” Paper presented at the ICLR 2018, Vancouver, BC, April 30-May 3, 2018, ICLR © 2018 The Author(s)
Version
Author's final manuscript
Abstract
In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different classification problems, each with a small labeled training set and its corresponding test set. In this work, we advance this few-shot classification paradigm towards a scenario where unlabeled examples are also available within each episode. We consider two situations: one where all unlabeled examples are assumed to belong to the same set of classes as the labeled examples of the episode, as well as the more challenging situation where examples from other distractor classes are also provided. To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes. These models are trained in an end-to-end way on episodes, to learn to leverage the unlabeled examples successfully. We evaluate these methods on versions of the Omniglot and miniImageNet benchmarks, adapted to this new framework augmented with unlabeled examples. We also propose a new split of ImageNet, consisting of a large set of classes, with a hierarchical structure. Our experiments confirm that our Prototypical Networks can learn to improve their predictions due to unlabeled examples, much like a semi-supervised algorithm would.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
