Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild

Lifelong learning with deep neural networks is wellknown to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large stream of unlabeled data easily obtainable in the wild. In particular, we design a novel classincremental learning scheme with (a) a new distillation loss, termed global distillation, (b) a learning strategy to avoid overfitting to the most recent task, and (c) a confidence-based sampling method to effectively leverage unlabeled external data. Our experimental results on various datasets, including CIFAR and ImageNet, demonstrate the superiority of the proposed methods over prior methods, particularly when a stream of unlabeled data is accessible: our method shows up to 15.8% higher accuracy and 46.5% less forgetting compared to the state-of-the-art method. The code is available at https://github. com/kibok90/iccv2019-inc . Unlabeled dataset sampled from A. We propose a new learning objective, termed global distillation, which utilizes data to distill the knowledge of reference models effectively.