Hierarchical Few-Shot Generative Models release_acgndbfvlvhadmk4r4be5ntma4

by Giorgio Giannone, Ole Winther

Released as a article .

2022  

Abstract

A few-shot generative model should be able to generate data from a distribution by only observing a limited set of examples. In few-shot learning the model is trained on data from many sets from different distributions sharing some underlying properties such as sets of characters from different alphabets or sets of images of different type objects. We extend current latent variable models for sets to a fully hierarchical approach with an attention-based point to set-level aggregation and call our approach SCHA-VAE for Set-Context-Hierarchical-Aggregation Variational Autoencoder. We explore iterative data sampling, likelihood-based model comparison, and adaptation-free out of distribution generalization. Our results show that the hierarchical formulation better captures the intrinsic variability within the sets in the small data regime. With this work we generalize deep latent variable approaches to few-shot learning, taking a step towards large-scale few-shot generation with a formulation that readily can work with current state-of-the-art deep generative models.
In text/plain format

Archived Files and Locations

application/pdf  2.5 MB
file_dexxgpewdrd75j6hpctjlv75pa
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-01-31
Version   v2
Language   en ?
arXiv  2110.12279v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 054c8d5f-26b1-49d6-8418-b27234452a88
API URL: JSON