As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for this task of continual learning, the best method for selecting which buffered images to replay is still an open question. In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. To this end, we contribute a novel Adversarial Shapley value scoring method that scores memory data samples according to their ability to preserve latent decision boundaries for previously observed classes (to maintain learning stability and avoid forgetting) while interfering with latent decision boundaries of current classes being learned (to encourage plasticity and optimal learning of new class boundaries). Overall, we observe that our proposed ASER method provides competitive or improved performance compared to state-of-the-art replay-based continual learning methods on a variety of datasets.
翻译:由于从手机到智能手表等各种设备都普遍进行基于图像的深层次学习,因此越来越需要制定方法,不断从数据中学习,同时尽量减少记忆足迹和动力消耗。虽然记忆回放技术为这一持续学习的任务显示了非凡的希望,但选择缓冲图像重播的最佳方法仍然是一个未决问题。在本文中,我们特别侧重于在线类入门设置,模型需要从在线数据流中不断学习新班级。为此,我们贡献了一种新颖的Aversarial Shapley评分方法,该方法根据它们为以往观察到的班级保留潜在决策界限的能力来评分记忆数据样本(以保持学习稳定性和避免遗忘),同时干扰当前班级的潜在决策界限(以鼓励塑料和最佳地学习新班级界限 ) 。 总的来说,我们观察到,我们提议的ASER方法在各种数据集上提供竞争性或改进性能,而不是以最新技术为基础的连续学习方法。