Related papers: Product of Orthogonal Spheres Parameterization for…

We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting. Our goal is to map an input image to an identity-invariant latent representation that captures…

The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with a distorted mapping…

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

Although data generation is often straightforward, extracting information from data is more difficult. Object-centric representation learning can extract information from images in an unsupervised manner. It does so by segmenting an image…

A variational autoencoder (VAE) derived from Tsallis statistics called q-VAE is proposed. In the proposed method, a standard VAE is employed to statistically extract latent space hidden in sampled data, and this latent space helps make…

We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE). Motivated by the…

Recently, the disentangled latent space of a variational autoencoder (VAE) has been used to reason about multi-label out-of-distribution (OOD) test samples that are derived from different distributions than training samples. Disentangled…

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream…

Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…

Despite the significant recent progress in deep generative models, the underlying structure of their latent spaces is still poorly understood, thereby making the task of performing semantically meaningful latent traversals an open research…

Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify.…

Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational…

The careful construction of audio representations has become a dominant feature in the design of approaches to many speech tasks. Increasingly, such approaches have emphasized "disentanglement", where a representation contains only parts of…

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data…

Learning disentangled causal representations is a challenging problem that has gained significant attention recently due to its implications for extracting meaningful information for downstream tasks. In this work, we define a new notion of…

Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically,…

A large part of the literature on learning disentangled representations focuses on variational autoencoders (VAE). Recent developments demonstrate that disentanglement cannot be obtained in a fully unsupervised setting without inductive…

In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear(in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private…

We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation learning concepts to make the disentangled latent…