Incremental learning with unlabeled data in the wild

Abstract

We propose to leverage a continuous and large stream of unlabeled data in the wild to alleviate catastrophic forgetting in class-incremental learning. Our experimental results on CIFAR and ImageNet datasets demonstrate the superiority of the proposed methods over prior methods: compared to the state-of-the-art method, our proposed method shows up to 14.9% higher accuracy and 45.9% less forgetting.