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 …

Image generating neural networks are mostly viewed as black boxes, where any change in
the input can have a number of globally effective changes on the output. In this work, we …

Capturing interpretable variations has long been one of the goals in disentanglement
learning. However, unlike the independence assumption, interpretability has rarely been …

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying
and disentangling the underlying factors hidden in the observable data in representation …

Inductive biases are crucial in disentangled representation learning for narrowing down an
underspecified solution set. In this work, we consider endowing a neural network …

Abstract Representation disentanglement is an important goal of the representation learning
that benefits various of downstream tasks. To achieve this goal, many unsupervised learning …

In this paper, we investigate the problem of learning disentangled representations. Given a
pair of images sharing some attributes, we aim to create a low-dimensional representation …

Learning representations that can disentangle explanatory attributes underlying the data
improves interpretabilty as well as provides control on data generation. Various learning …

Disentangling data into interpretable and independent factors is critical for controllable
generation tasks. With the availability of labeled data, supervision can help enforce the …

From the intuitive notion of disentanglement, the image variations corresponding to different
factors should be distinct from each other, and the disentangled representation should …