Distillation Techniques for Pseudo-rehearsal Based Incremental Learning
arXiv:1807.02799
Abstract
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained on incrementally arriving data. We discuss the biases in current Generative Adversarial Networks (GAN) based approaches that learn the classifier by knowledge distillation from previously trained classifiers. These biases cause the trained classifier to perform poorly. We propose an approach to remove these biases by distilling knowledge from the classifier of AC-GAN. Experiments on MNIST and CIFAR10 show that this method is comparable to current state of the art rehearsal based approaches. The code for this paper is available at https://bit.ly/incremental-learning
References in corpus (10)
- Distilling the Knowledge in a Neural Network
- Conditional Generative Adversarial Nets
- Overcoming catastrophic forgetting in neural networks
- Generative Adversarial Text to Image Synthesis
- Conditional Image Synthesis With Auxiliary Classifier GANs
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- Gradient Episodic Memory for Continual Learning
- FearNet: Brain-Inspired Model for Incremental Learning
- Incremental Classifier Learning with Generative Adversarial Networks
- A Strategy for an Uncompromising Incremental Learner