Online Class-Incremental Continual Learning with Adversarial Shapley Value

As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need develop methods that continually learn data while minimizing memory footprint and power consumption. While replay techniques have shown exceptional promise for this task of continual learning, the best method selecting which buffered images still an open question. In paper, we specifically focus online class-incremental setting where model needs new classes stream. To end, contribute novel Adversarial Shapley value scoring scores samples according their ability preserve latent decision boundaries previously observed (to maintain stability avoid forgetting) interfering with current being learned encourage plasticity optimal class boundaries). Overall, observe our proposed ASER provides competitive or improved performance compared state-of-the-art replay-based variety datasets.