Learning latent representations across multiple data domains using Lifelong VAEGAN
arXiv:2007.10221
Abstract
The problem of catastrophic forgetting occurs in deep learning models trained on multiple databases in a sequential manner. Recently, generative replay mechanisms (GRM), have been proposed to reproduce previously learned knowledge aiming to reduce the forgetting. However, such approaches lack an appropriate inference model and therefore can not provide latent representations of data. In this paper, we propose a novel lifelong learning approach, namely the Lifelong VAEGAN (L-VAEGAN), which not only induces a powerful generative replay network but also learns meaningful latent representations, benefiting representation learning. L-VAEGAN can allow to automatically embed the information associated with different domains into several clusters in the latent space, while also capturing semantically meaningful shared latent variables, across different data domains. The proposed model supports many downstream tasks that traditional generative replay methods can not, including interpolation and inference across different data domains.
Accepted as a conference paper at ECCV 2020
References in corpus (21)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Distilling the Knowledge in a Neural Network
- Overcoming catastrophic forgetting in neural networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Adversarial Feature Learning
- Adversarially Learned Inference
- Autoencoding beyond pixels using a learned similarity metric
- On Tiny Episodic Memories in Continual Learning
- Adversarial Autoencoders
- Continual Learning with Deep Generative Replay
- Less-forgetting Learning in Deep Neural Networks
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
- A Deep Hierarchical Approach to Lifelong Learning in Minecraft
- Lifelong Generative Modeling
- Continual Unsupervised Representation Learning
- Online Continual Learning with Maximally Interfered Retrieval
- Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
- Learning Disentangled Joint Continuous and Discrete Representations
- Adversarial Symmetric Variational Autoencoder
- Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
- Symmetric Variational Autoencoder and Connections to Adversarial Learning