Related papers: Learning Disentangled Representations with Latent …

Estimating individual-level treatment effect from observational data is a fundamental problem in causal inference and has attracted increasing attention in the fields of education, healthcare, and public policy.In this work, we concentrate…

Face images are subject to many different factors of variation, especially in unconstrained in-the-wild scenarios. For most tasks involving such images, e.g. expression recognition from video streams, having enough labeled data is…

Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the…

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,…

Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In this paper, we summarize the results of Locatello et al.,…

Learning fair representation is crucial for achieving fairness or debiasing sensitive information. Most existing works rely on adversarial representation learning to inject some invariance into representation. However, adversarial learning…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for…

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…

Recent disentangled representation learning (DRL) methods heavily rely on factor specific strategies-either learning objectives for attributes or model architectures for objects-to embed inductive biases. Such divergent approaches result in…

While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict independence in…

Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of this, the task of learning distributed representations of…

Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between…

While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However,…

Learning to disentangle and represent factors of variation in data is an important problem in AI. While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement. While several metrics…

The performance of $\beta$-Variational-Autoencoders ($\beta$-VAEs) and their variants on learning semantically meaningful, disentangled representations is unparalleled. On the other hand, there are theoretical arguments suggesting the…

Recently in the field of unsupervised representation learning, strong identifiability results for disentanglement of causally-related latent variables have been established by exploiting certain side information, such as class labels, in…