RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation
This work addresses forgetting in continual learning for segmentation, but it is incremental as it extends a previous method with adversarial and adaptive techniques.
The paper tackles catastrophic forgetting in continual learning for semantic segmentation by using unsupervised web-crawled data to retrieve old class examples, achieving remarkable results in multi-step incremental scenarios.
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. In contrast to the original methodology, which did not incorporate an assessment of web-based data, the present work proposes two advanced techniques: an adversarial approach and an adaptive threshold strategy. These methods are utilized to meticulously choose samples from web data that exhibit strong statistical congruence with the no longer available training data. Furthermore, we improved the pseudo-labeling scheme to achieve a more accurate labeling of web data that also considers classes being learned in the current step. Experimental results show that this enhanced approach achieves remarkable results, particularly when the incremental scenario spans multiple steps.