Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

31

Series

Transactions on Machine Learning Research, Volume 2025-June

Abstract

Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable latent space or discover interpretable directions, which requires exploiting data labels or annotated synthesized samples for training. However, we propose using a modification of vector quantization called space-filling vector quantization (SFVQ), which quantizes the data on a piece-wise linear curve. SFVQ can capture the underlying morphological structure of the latent space, making it interpretable. We apply this technique to model the latent space of pre-trained StyleGAN2 and BigGAN networks on various datasets. Our experiments show that the SFVQ curve yields a general interpretable model of the latent space such that it determines which parts of the latent space correspond to specific generative factors. Furthermore, we demonstrate that each line of the SFVQ curve can potentially refer to an interpretable direction for applying intelligible image transformations. We also demonstrate that the points located on an SFVQ line can be used for controllable data augmentation.

Description

Publisher Copyright: © 2025, Transactions on Machine Learning Research. All rights reserved.

Keywords

Other note

Citation

Vali, M H & Bäckström, T 2025, 'Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization', Transactions on Machine Learning Research, vol. 2025-June. < https://openreview.net/forum?id=SEJatSGZX8 >