ContinualAI RG: “ACAE-REMIND for Online Continual Learning with Compressed Feature Replay“

This Friday 06-11-2021, CEST, for the ContinualAI Reading Group, Kai Wang will present the paper: Title: “ACAE-REMIND for Online Continual Learning with Compressed Feature Replay” Abstract: Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for featur