Demystifying Inter-Class DisentanglementDownload PDF

Published: 20 Dec 2019, Last Modified: 05 May 2023ICLR 2020 Conference Blind SubmissionReaders: Everyone
TL;DR: Latent Optimization for Representation Disentanglement
Abstract: Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent Optimization for Representation Disentanglement. We find that latent optimization, along with an asymmetric noise regularization, is superior to amortized inference for achieving disentangled representations. In extensive experiments, our method is shown to achieve better disentanglement performance than both adversarial and non-adversarial methods that use the same level of supervision. We further introduce a clustering-based approach for extending our method for settings that exhibit in-class variation with promising results on the task of domain translation.
Code: https://github.com/avivga/lord
Keywords: disentanglement, latent optimization, domain translation
Original Pdf: pdf
11 Replies

Loading