Demystifying Inter-Class Disentanglement.

Aviv Gabbay, Yedid Hoshen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


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.
Original languageEnglish
Title of host publicationICLR 2020
Subtitle of host publicationInternational Conference on Learning Representations
Number of pages17
StatePublished - 2020
EventInternational Conference on Learning Representations, ICLR 2020
- Virtual event
Duration: 26 Apr 20201 May 2020


ConferenceInternational Conference on Learning Representations, ICLR 2020
Abbreviated titleICLR 2020
Internet address


  • Disentanglement
  • Latent optimization
  • Domain translation


Dive into the research topics of 'Demystifying Inter-Class Disentanglement.'. Together they form a unique fingerprint.

Cite this