Related papers: Disentanglement Beyond Static vs. Dynamic: A Bench…

It has been a hot research topic to enable machines to understand human emotions in multimodal contexts under dialogue scenarios, which is tasked with multimodal emotion analysis in conversation (MM-ERC). MM-ERC has received consistent…

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disentangled representations were found to be useful for diverse…

Correlations between factors of variation are prevalent in real-world data. Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e.g., they may change between domains,…

Sensory data are often comprised of independent content and transformation factors. For example, face images may have shapes as content and poses as transformation. To infer separately these factors from given data, various…

This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations. Within this framework, we establish identifiability conditions for general disentangled latent variable models,…

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample efficiency for…

Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced…

One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature…

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label…

The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we…

Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

As face recognition is widely used in diverse security-critical applications, the study of face anti-spoofing (FAS) has attracted more and more attention. Several FAS methods have achieved promising performances if the attack types in the…

We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer…

Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions,…

This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors. We propose a…

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…

Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents. Higgins et al.…