Lifelong learning of interpretable image representations

By Fei Ye, Adrian G. Bors. 2020

13 citations recorded by the source corpus.

Existing machine learning systems are trained to adapt to a single database and their ability to acquire additional information is limited. Catastrophic forgetting occurs in all deep learning systems when attempting to train them with additional databases. The information learnt previously is forgotten and no longer recognized when such a learning systems is trained using a new database. In this paper, we develop a new image generation approach defined under the lifelong learning framework which prevents forgetting. We employ the mutual information maximization between the latent variable space and the outputs of the generator network in order to learn interpretable representations, when learning using the data from a series of databases sequentially. We also provide the theoretical framework for the generative replay mechanism, under the lifelong learning setting. We perform a series of experiments showing that the proposed approach is able to learn a set of disjoint data distributions in a sequential manner while also capturing meaningful data representations across domains.

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

1. Fei Ye
2. Adrian G. Bors

In Computer Vision and Pattern Recognition

1. Fei Ye
2. Adrian G. Bors

Citations in the corpus

• Task-Free Continual Learning via Online Discrepancy Distance Learning (2022, neutral): “Another kind of approaches for continual learning focuses on the memory system, which usually employs a small memory buffer [1, 5, 6, 28, 36, 44, 59] to store a few past data or trains a generator to provide the replay samples when learning new tasks [38, 43, 46, 47, 52, 58, 53].”
• InfoVAEGAN: Learning Joint Interpretable Representations by Information Maximization and Maximum Likelihood (2021, unknown): “According to the research study from [14] it is difficult to optimize the mutual information directly, given that it needs to access the information represented by the true posterior p(u|x).”
• Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process (2021, background): “Memory replay approaches would either use a generator [1, 34, 33, 41, 56, 51, 52, 55, 57] or a memory buffer [2, 4, 46] as a replay mechanism generating data, which is statistically consistent to the previously learnt knowledge.”
• Continual Variational Autoencoder Learning via Online Cooperative Memorization (2022, background): “Other approaches would employ a small buffer to store a few past data [3,10,53] or would train a generator as a generative replay network that provides pseudo data samples for the future task learning [2,44,45,49,57,58,59,66,69].”
• 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].”