Evaluating Disentanglement of Structured Latent Representations
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementObjectSimilar Papers 제목 키워드 기반
Evaluating Disentanglement of Structured Representations
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…
DisentanglementObjectEvaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes
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 GenerationMultifactor Sequential Disentanglement via Structured Koopman Autoencoders
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 LearningA Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation
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
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