DeepAI AI Chat
Log In Sign Up

GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images

by   Aadhithya Sankar, et al.

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 that require a large number of labelled or unlabelled data. Recently, flow-based generative models have been proposed to generate realistic images by directly modeling the data distribution with invertible functions. In this work, we propose a new flow-based generative model framework, named GLOWin, that is end-to-end invertible and able to learn disentangled representations. Feature disentanglement is achieved by factorizing the latent space into components such that each component learns the representation for one generative factor. Comprehensive experiments have been conducted to evaluate the proposed method on a public brain tumor MR dataset. Quantitative and qualitative results suggest that the proposed method is effective in disentangling the features from complex medical images.


page 6

page 7

page 10


Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions

Disentangled visual representations have largely been studied with gener...

Inferencing Based on Unsupervised Learning of Disentangled Representations

Combining Generative Adversarial Networks (GANs) with encoders that lear...

RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior

Flow-based generative models have become an important class of unsupervi...

Learning Disentangled Representations via Independent Subspaces

Image generating neural networks are mostly viewed as black boxes, where...

The pursuit of beauty: Converting image labels to meaningful vectors

A challenge of the computer vision community is to understand the semant...

Generative Multiple-Instance Learning Models For Quantitative Electromyography

We present a comprehensive study of the use of generative modeling appro...