paper-with-me

홈 › Papers

Evaluating Disentanglement of Structured Latent Representations

2021-09-29 · ICLR 2022 4 · Raphaël Dang-Nhu

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementObject

Similar Papers 제목 키워드 기반

Evaluating Disentanglement of Structured Representations

2021-01-11 · Raphaël Dang-Nhu

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 t…

DisentanglementObject

Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes

2021-10-11 · Karn N. Watcharasupat, Alexander Lerch

Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often …

DisentanglementMusic Generation

Multifactor Sequential Disentanglement via Structured Koopman Autoencoders

2023-03-30 · Nimrod Berman, Ilan Naiman, Omri Azencot

Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates t…

DisentanglementInductive BiasRepresentation Learning

A Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation

2026-03-11 · Xiaoan Lang, Md Mostafizer Rahman, Fang Liu arxiv

Evaluating and interpreting latent representations, such as variational autoencoders (VAEs), remains a significant challenge for diverse data types, especially when ground-truth generative factors are unknown. To address…

Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors

2022-11-15 · Anjun Hu, Jean-Pierre R. Falet, Brennan S. Nichyporuk, Changjian Shui 외

We propose a hierarchically structured variational inference model for accurately disentangling observable evidence of disease (e.g. brain lesions or atrophy) from subject-specific anatomy in brain MRIs. With flexible, p…

AnatomyDisentanglementVariational Inference