Evaluating Disentanglement of Structured RepresentationsDownload PDF

Published: 28 Jan 2022, Last Modified: 04 May 2025ICLR 2022 PosterReaders: Everyone
Abstract: We introduce the first metric for evaluating disentanglement at individual hierarchy levels of a structured latent representation. Applied to object-centric generative models, this offers a systematic, unified approach to evaluating (i) object separation between latent slots (ii) disentanglement of object properties inside individual slots (iii) disentanglement of intrinsic and extrinsic object properties. We theoretically show that our framework gives stronger guarantees of selecting a good model than previous disentanglement metrics. Experimentally, we demonstrate that viewing object compositionality as a disentanglement problem addresses several issues with prior visual metrics of object separation. As a core technical component, we present the first representation probing algorithm handling slot permutation invariance.
One-sentence Summary: We introduce the first metric for evaluating disentanglement at individual hierarchy levels of a structured latent representation, and apply it to object-centric generative models.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/evaluating-disentanglement-of-structured/code)
21 Replies

Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview