Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation

Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the latter methods employ modality-based data augmentations and random sampling or...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-05
Main Authors: Naiman, Ilan, Berman, Nimrod, Azencot, Omri
Format: Article
Language:English
Subjects:
Audio data
Data augmentation
Random sampling
Time dependence
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the latter methods employ modality-based data augmentations and random sampling or solve auxiliary tasks. In this work, we propose to avoid that by generating, sampling, and comparing empirical distributions from the underlying variational model. Unlike existing work, we introduce a self-supervised sequential disentanglement framework based on contrastive estimation with no external signals, while using common batch sizes and samples from the latent space itself. In practice, we propose a unified, efficient, and easy-to-code sampling strategy for semantically similar and dissimilar views of the data. We evaluate our approach on video, audio, and time series benchmarks. Our method presents state-of-the-art results in comparison to existing techniques. The code is available at https://github.com/azencot-group/SPYL.
ISSN:2331-8422