Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed. In this paper, we extend our previous approach (RECALL) and tackle forgetting by exploiting unsupervised web-crawled data to retrieve examples of old classes from online databases. Differently from the original approach that did not perform any evaluation of the web data, here we introduce two novel approaches based on adversarial learning and adaptive thresholding to select from web data only samples strongly resembling the statistics of the no longer available training ones. Furthermore, we improved the pseudo-labeling scheme to achieve a more accurate labeling of web data that also consider classes being learned in the current step. Experimental results show that this enhanced approach achieves remarkable results, especially when multiple incremental learning steps are performed.

通过利用无监督的网络爬取数据检索旧类别示例，本文拓展了之前的方法（RECALL）并通过对抗学习和自适应阈值选择与当前训练数据相似的网络数据样本以解决持续学习中的遗忘问题，在多个增量学习步骤中表现出卓越的结果。

RECALL+: 广告网络回放对语义分割中的持续学习