University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Nested VAE:Isolating Common Factors via Weak Supervision

Vowels, Matthew, Camgöz, Necati Cihan and Bowden, Richard (2020) Nested VAE:Isolating Common Factors via Weak Supervision In: 15th IEEE International Conference on Automatic Face and Gesture Recognition, Postponed to 6th-10th November, 2020, Buenos Aires, Argentina.

[img]
Preview
Text
05477.pdf - Accepted version Manuscript

Download (1MB) | Preview

Abstract

Fair and unbiased machine learning is an important and active field of research, as decision processes are increasingly driven by models that learn from data. Unfortunately, any biases present in the data may be learned by the model, thereby inappropriately transferring that bias into the decision making process. We identify the connection between the task of bias reduction and that of isolating factors common between domains whilst encouraging domain specific invariance. To isolate the common factors we combine the theory of deep latent variable models with information bottleneck theory for scenarios whereby data may be naturally paired across domains and no additional supervision is required. The result is the Nested Variational AutoEncoder (NestedVAE). Two outer VAEs with shared weights attempt to reconstruct the input and infer a latent space, whilst a nested VAE attempt store construct the latent representation of one image,from the latent representation of its paired image. In so doing,the nested VAE isolates the common latent factors/causes and becomes invariant to unwanted factors that are not shared between paired images. We also propose a new metric to provide a balanced method of evaluating consistency and classifier performance across domains which we refer to as the Adjusted Parity metric. An evaluation of Nested VAE on both domain and attribute invariance, change detection,and learning common factors for the prediction of biological sex demonstrates that NestedVAE significantly outperforms alternative methods.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Vowels, Matthewm.vowels@surrey.ac.uk
Camgöz, Necati Cihann.camgoz@surrey.ac.uk
Bowden, RichardR.Bowden@surrey.ac.uk
Date : 26 February 2020
Funders : SNSF Sinergia, European Union’s Horizon2020 research and innovation programme, EPSRC
Grant Title : ExTOL
Depositing User : James Marshall
Date Deposited : 02 Apr 2020 15:20
Last Modified : 02 Apr 2020 15:20
URI: http://epubs.surrey.ac.uk/id/eprint/854112

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800