Learning joint latent representations based on information maximization
By Fei Ye, Adrian G. Bors. 2021
29 citations recorded by the source corpus.
Abstract Learning disentangled and interpretable representations is an important aspect of information understanding. In this paper, we propose a novel deep learning model representing both discrete and continuous latent variable spaces which can be used in either supervised or unsupervised learning. The proposed model is trained using an optimization function employing the mutual information maximization criterion. For the unsupervised learning setting we define a lower bound to the mutual information between the joint distribution of the latent variables corresponding to the real data and those generated by the model. The maximization of this lower bound during the training induces the learning of disentangled and interpretable data representations. Such representations can be used for attribute manipulation and image editing tasks.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Task-Free Continual Learning via Online Discrepancy Distance Learning (2022, neutral): “Due to its robust generation and inference mechanisms, VAEs have been widely used in many applications [48, 49, 50, 51, 54, 61].”
- Continual Variational Autoencoder Learning via Online Cooperative Memorization (2022, methodology): “VAEs have been widely used in image synthesis [60,62], semi-supervised learning [1,63] and for image-to-image translation [38].”
- Learning an Evolved Mixture Model for Task-Free Continual Learning (2022, background): “However, deep learning systems would usually perform well on individual tasks [2, 3] but suffer from dramatic performance loss when training on several different tasks sequentially [4, 5, 6].”
- Lifelong Twin Generative Adversarial Networks (2021, methodology): “We enable the Student for learning dissentangled representations [18, 19] by penalizing the Kullback-Leibler divergence between the posterior and prior distributions, [20] :”
- Deep Mixture Generative Autoencoders (2021, background): “Mixed GAN and VAE architectures have been enabled with representation learning capabilities [16], [17].”
- Lifelong Generative Modelling Using Dynamic Expansion Graph Model (2021, methodology): “2018), for disentangled representation learning (Higgins et al. 2017; Ye and Bors 2021d) and for image reconstruction tasks (Ye and Bors 2020c, 2021b,c,d).”
- InfoVAEGAN: Learning Joint Interpretable Representations by Information Maximization and Maximum Likelihood (2021, background): “Learning disentangled representations that may capture semantic meaningful information can allow to explicitly edit images and is useful for a variety of tasks [1, 2, 3].”