Related papers: Disentangling Domain and Content

There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously…

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…

Limited amount of labelled training data are a common problem in medical imaging. This makes it difficult to train a well-generalised model and therefore often leads to failure in unknown domains. Hippocampus segmentation from magnetic…

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…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Learning on synthetic data and transferring the resulting properties to their real counterparts is an important challenge for reducing costs and increasing safety in machine learning. In this work, we focus on autoencoder architectures and…

Generalization capabilities of learning-based medical image segmentation across domains are currently limited by the performance degradation caused by the domain shift, particularly for ultrasound (US) imaging. The quality of US images…

Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. Although domain adaptive crowd counting approaches close this gap to a certain extent, they are still dependent on the target domain…

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…

Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models…

Representation learning seeks meaningful sensory representations without supervision and can model aspects of human development. Although many neural networks empirically learn useful features, a principled account of what makes a…

There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their…

A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially equivariant tasks…

Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source domain training data is more challenging due to the lack of…

Disentangled distributed representations of data are desirable for machine learning, since they are more expressive and can generalize from fewer examples. However, for complex data, the distributed representations of multiple objects…

Multi-modal domain translation typically refers to synthesizing a novel image that inherits certain localized attributes from a 'content' image (e.g. layout, semantics, or geometry), and inherits everything else (e.g. texture, lighting,…

Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art…

In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting…

We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the…

Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations…