Collaborative Method for Incremental Learning on Classification and Generation
This addresses the problem of data deficiency and forgetting for incremental learning in AI, but it is incremental as it builds on existing methods.
The paper tackles catastrophic forgetting in deep neural networks during incremental class learning by introducing ICLAS, which trains classification and generation networks together, and shows advantages on MNIST dataset.
Although well-trained deep neural networks have shown remarkable performance on numerous tasks, they rapidly forget what they have learned as soon as they begin to learn with additional data with the previous data stop being provided. In this paper, we introduce a novel algorithm, Incremental Class Learning with Attribute Sharing (ICLAS), for incremental class learning with deep neural networks. As one of its component, we also introduce a generative model, incGAN, which can generate images with increased variety compared with the training data. Under challenging environment of data deficiency, ICLAS incrementally trains classification and the generation networks. Since ICLAS trains both networks, our algorithm can perform multiple times of incremental class learning. The experiments on MNIST dataset demonstrate the advantages of our algorithm.