Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

TL;DR

This paper introduces a comprehensive benchmark and evaluation framework for multi-factor sequential disentanglement in deep learning, addressing the complexity of real-world data involving multiple interacting semantic factors over time.

Contribution

It presents the first standardized benchmark, modular tools, a post-hoc Latent Exploration Stage, a Koopman-inspired model, and leverages Vision-Language Models for automated dataset annotation and evaluation.

Findings

Koopman-inspired model achieves state-of-the-art results.

Vision-Language Models enable zero-shot disentanglement evaluation.

Benchmark spans six diverse datasets across modalities.

Abstract

Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work has mostly focused on simpler two-factor static and dynamic settings, primarily because such settings make data collection easier, thereby overlooking the inherently multi-factor nature of real-world data. We introduce the first standardized benchmark for evaluating multi-factor sequential disentanglement across six diverse datasets spanning video, audio, and time series. Our benchmark includes modular tools for dataset integration, model development, and evaluation metrics tailored to multi-factor analysis. We additionally propose a post-hoc Latent Exploration Stage to automatically align latent dimensions with semantic factors, and introduce a Koopman-inspired model that achieves state-of-the-art results. Moreover, we show that Vision-Language Models can automate dataset annotation and serve as zero-shot disentanglement evaluators, removing the need for manual labels and human intervention. Together, these contributions provide a robust and scalable foundation for advancing multi-factor sequential disentanglement. Our code is available on GitHub, and the datasets and trained models are available on Hugging Face.