FlowReg: latent space regularization using normalizing flow for limited samples learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

48 Downloads (Pure)

Abstract

Modern deep neural network models have made remarkable success in many areas, supported by large sets of training samples. Yet the hunger for huge data has also become fatal in further expanding the use of deep models. Limited sample learning aims at learning generalized and transferable representations, without requiring large training data. In this paper, we propose FlowReg, a new learnable latent space regularization for limited sample problems. FlowReg modulates the latent space using a Normalizing Flow with a simple prior (such as Gaussian) while maintaining the complexity of the posterior distribution. We conduct thorough experiments on diverse tasks in limited label learning, as well as detailed in-depth analysis to comprehensively demonstrate the effectiveness of FlowReg.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Electronic)9781728163277
ISBN (Print)9781728163284
DOIs
Publication statusPublished - 04 Jun 2023
EventIEEE International Conference on Acoustics, Speech, and Signal Processing 2023 - Rhodes, Greece
Duration: 04 Jun 202310 Jun 2023
https://doi.org/10.1109/ICASSP49357.2023

Publication series

NameInternational Conference on Acoustics, Speech, and Signal Processing: Proceedings
PublisherIEEE
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing 2023
Abbreviated titleICASSP 2023
Country/TerritoryGreece
CityRhodes
Period04/06/202310/06/2023
Internet address

Fingerprint

Dive into the research topics of 'FlowReg: latent space regularization using normalizing flow for limited samples learning'. Together they form a unique fingerprint.

Cite this