Autoencoder-Based Incremental Class Learning without Retraining on Old Data
This addresses memory efficiency for incremental learning in AI systems, though it is incremental as it builds on existing regularization and metric-based approaches.
The paper tackles catastrophic forgetting in incremental class learning by proposing an autoencoder-based method that stores only class prototype means, achieving performance comparable to state-of-the-art with significantly lower memory overhead on datasets like CIFAR-100 and CUB-200-2011.
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.