Timezone: »
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 \emph{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.
Author Information
Giorgio Giannone (Technical University of Denmark (DTU))
Ole Winther (DTU and KU)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Hierarchical Few-Shot Generative Models »
Dates n/a. Room None
More from the Same Authors
-
2021 : Representation Learning for Out-of-distribution Generalization in Downstream Tasks »
Frederik Träuble · Andrea Dittadi · Manuel Wüthrich · Felix Widmaier · Peter Gehler · Ole Winther · Francesco Locatello · Olivier Bachem · Bernhard Schölkopf · Stefan Bauer -
2022 Poster: Generalization and Robustness Implications in Object-Centric Learning »
Andrea Dittadi · Samuele Papa · Michele De Vita · Bernhard Schölkopf · Ole Winther · Francesco Locatello -
2022 Spotlight: Generalization and Robustness Implications in Object-Centric Learning »
Andrea Dittadi · Samuele Papa · Michele De Vita · Bernhard Schölkopf · Ole Winther · Francesco Locatello -
2022 : Inductive Biases for Object-Centric Representations in the Presence of Complex Textures »
Samuele Papa · Ole Winther · Andrea Dittadi