Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jun, Youngjun, Park, Jiwoo, Choo, Kyobin, Choi, Tae Eun, Hwang, Seong Jae
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909373696049152
author Jun, Youngjun
Park, Jiwoo
Choo, Kyobin
Choi, Tae Eun
Hwang, Seong Jae
author_facet Jun, Youngjun
Park, Jiwoo
Choo, Kyobin
Choi, Tae Eun
Hwang, Seong Jae
contents Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making unsupervised methods attractive. Recently, there have been limited explorations of utilizing diffusion models (DMs), which are already mainstream in generative modeling, for unsupervised DRL. They implement their own inductive bias to ensure that each latent unit input to the DM expresses only one distinct factor. In this context, we design Dynamic Gaussian Anchoring to enforce attribute-separated latent units for more interpretable DRL. This unconventional inductive bias explicitly delineates the decision boundaries between attributes while also promoting the independence among latent units. Additionally, we also propose Skip Dropout technique, which easily modifies the denoising U-Net to be more DRL-friendly, addressing its uncooperative nature with the disentangling feature extractor. Our methods, which carefully consider the latent unit semantics and the distinct DM structure, enhance the practicality of DM-based disentangled representations, demonstrating state-of-the-art disentanglement performance on both synthetic and real data, as well as advantages in downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23820
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
Jun, Youngjun
Park, Jiwoo
Choo, Kyobin
Choi, Tae Eun
Hwang, Seong Jae
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making unsupervised methods attractive. Recently, there have been limited explorations of utilizing diffusion models (DMs), which are already mainstream in generative modeling, for unsupervised DRL. They implement their own inductive bias to ensure that each latent unit input to the DM expresses only one distinct factor. In this context, we design Dynamic Gaussian Anchoring to enforce attribute-separated latent units for more interpretable DRL. This unconventional inductive bias explicitly delineates the decision boundaries between attributes while also promoting the independence among latent units. Additionally, we also propose Skip Dropout technique, which easily modifies the denoising U-Net to be more DRL-friendly, addressing its uncooperative nature with the disentangling feature extractor. Our methods, which carefully consider the latent unit semantics and the distinct DM structure, enhance the practicality of DM-based disentangled representations, demonstrating state-of-the-art disentanglement performance on both synthetic and real data, as well as advantages in downstream tasks.
title Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.23820