We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiological evidence that the primary visual cortex does not contribute to object manifold untangling for categorization and that primordial attention biases are still embedded in the modern brain, we propose to employ auxiliary saliency prediction features as a modulation signal to drive and stabilize the learning of a sequence of non-i.i.d. classification tasks. Experimental results confirm that SAM effectively enhances the performance (in some cases up to about twenty percent points) of state-of-the-art continual learning methods, both in class-incremental and task-incremental settings. Moreover, we show that attention-based modulation successfully encourages the learning of features that are more robust to the presence of spurious features and to adversarial attacks than baseline methods. Code is available at: https://github.com/perceivelab/SAM.

翻译：我们提出SAM，一种受神经生物学启发的选择性注意驱动调制方法，用于在持续学习场景中增强分类模型性能。受以下神经生理学证据启发：初级视觉皮层不参与物体流形解缠以进行分类，且原始注意偏向仍嵌于现代大脑中，我们提出利用辅助显著特征预测作为调制信号，驱动并稳定一系列非独立同分布分类任务的学习。实验结果表明，SAM能有效提升最先进持续学习方法的性能（某些情况下提升高达约二十个百分点），且该方法同时适用于类增量与任务增量学习场景。此外，我们证明基于注意的调制方法所学习的特征比基线方法对虚假特征和对抗攻击具有更强鲁棒性。代码开源地址：https://github.com/perceivelab/SAM。