Learning Disentangled Representations via Mutual Information Estimation
This work addresses the challenge of representation disentanglement for downstream tasks like image classification and retrieval, offering a novel approach that could benefit machine learning applications in computer vision.
The paper tackles the problem of learning disentangled representations from image pairs by proposing a model that uses mutual information estimation to separate shared and exclusive components without relying on reconstruction or generation, and it shows improved performance in classification tasks over VAE/GAN-based methods.
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 which is split into two parts: a shared representation that captures the common information between the images and an exclusive representation that contains the specific information of each image. To address this issue, we propose a model based on mutual information estimation without relying on image reconstruction or image generation. Mutual information maximization is performed to capture the attributes of data in the shared and exclusive representations while we minimize the mutual information between the shared and exclusive representation to enforce representation disentanglement. We show that these representations are useful to perform downstream tasks such as image classification and image retrieval based on the shared or exclusive component. Moreover, classification results show that our model outperforms the state-of-the-art model based on VAE/GAN approaches in representation disentanglement.