Continual Learning in Generative Adversarial Nets

05/23/2017
by   Ari Seff, et al.
0

Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest, it may be desirable to model distinct distributions which are observed sequentially, such as when different classes are encountered over time. Although conditional variations of deep generative models permit multiple distributions to be modeled by a single network in a disentangled fashion, they are susceptible to catastrophic forgetting when the distributions are encountered sequentially. In this paper, we adapt recent work in reducing catastrophic forgetting to the task of training generative adversarial networks on a sequence of distinct distributions, enabling continual generative modeling.

READ FULL TEXT

page 6

page 7

page 8

research
10/24/2018

Continual Classification Learning Using Generative Models

Continual learning is the ability to sequentially learn over time by acc...
research
05/17/2023

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

The recent proliferation of large-scale text-to-image models has led to ...
research
05/19/2023

Few-Shot Continual Learning for Conditional Generative Adversarial Networks

In few-shot continual learning for generative models, a target mode must...
research
03/09/2020

FoCL: Feature-Oriented Continual Learning for Generative Models

In this paper, we propose a general framework in continual learning for ...
research
11/13/2020

Population synthesis for urban resident modeling using deep generative models

The impacts of new real estate developments are strongly associated to i...
research
05/24/2017

Continual Learning with Deep Generative Replay

Attempts to train a comprehensive artificial intelligence capable of sol...
research
06/16/2023

Understanding Deep Generative Models with Generalized Empirical Likelihoods

Understanding how well a deep generative model captures a distribution o...

Please sign up or login with your details

Forgot password? Click here to reset