Autoencoder-Based Incremental Class Learning without Retraining on Old Data

Abstract

Incremental class learning, a scenario in continual learning context where classes and their training data are sequentially and disjointedly observed, challenges a problem widely known as catastrophic forgetting. In this work, we propose a novel incremental class learning method that can significantly reduce memory overhead compared to previous approaches. Apart from conventional classification scheme using softmax, our model bases on an autoencoder to extract prototypes for given inputs so that no change in its output unit is required. It stores only the mean of prototypes per class to perform metric-based classification, unlike rehearsal approaches which rely on large memory or generative model. To mitigate catastrophic forgetting, regularization methods are applied on our model when a new task is encountered. We evaluate our method by experimenting on CIFAR-100 and CUB-200-2011 and show that its performance is comparable to the state-of-the-art method with much lower additional memory cost.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• On the Convergence of Adam and Beyond
• Continual Learning Through Synaptic Intelligence
• Overcoming catastrophic forgetting with hard attention to the task
• Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
• Measuring Catastrophic Forgetting in Neural Networks
• Incremental Classifier Learning with Generative Adversarial Networks
• Deep Discriminant Analysis for i-vector Based Robust Speaker Recognition

Cited by in corpus (3)

• Structure-preserving neural networks
• Continual Learning with Adaptive Weights (CLAW)
• Incremental Class Learning using Variational Autoencoders with Similarity Learning