缓解在线类增量学习中任务近期偏倚的新见解
New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning
AI总结：
针对在线类增量学习中的稳定性-可塑性困境，提出自适应焦点转移算法（AFS），通过修正focal loss关注模糊样本以保持稳定性，并引入虚拟知识蒸馏关注非目标类以提升可塑性，在三个数据集上验证了有效性。
摘要：
为了模仿人类不断学习的能力，能够从无尽数据流中学习的持续学习最近引起了更多关注。在所有设置中，在线类增量学习（OCIL）中来自数据流的输入样本只能使用一次，这更具挑战性且在现实世界中更常遇到。实际上，所有持续学习模型都面临稳定性-可塑性困境，其中稳定性指保留旧知识的能力，而可塑性指吸收新知识的能力。尽管基于回放的方法展现出非凡前景，但大多数方法集中于更新和检索记忆的策略，以牺牲可塑性为代价来保持稳定性。为了在稳定性和可塑性之间取得更好的权衡，我们提出了一种自适应焦点转移算法（AFS），它在模型学习中动态调整对模糊样本和非目标 logits 的关注。通过对类不平衡引起的任务近期偏倚进行深入分析，我们提出了一种修正的 focal loss 以主要保持稳定性。通过利用新的权重函数，修正的 focal loss 将更多关注当前的模糊样本，这些样本是使模型快速进步的潜在有价值样本。为了促进可塑性，我们引入了虚拟知识蒸馏。通过设计虚拟教师，它将更多注意力分配给非目标类，这可以克服过度自信并鼓励模型关注类间信息。在三个流行的 OCIL 数据集上的大量实验表明了 AFS 的有效性。代码将发布在 https://github.com/czjghost/AFS。
英文摘要：
To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming samples from data stream can be used only once, is more challenging and can be encountered more frequently in real world. Actually, all continual learning models face a stability-plasticity dilemma, where the stability means the ability to preserve old knowledge while the plasticity denotes the ability to incorporate new knowledge. Although replay-based methods have shown exceptional promise, most of them concentrate on the strategy for updating and retrieving memory to keep stability at the expense of plasticity. To strike a preferable trade-off between stability and plasticity, we propose an Adaptive Focus Shifting algorithm (AFS), which dynamically adjusts focus to ambiguous samples and non-target logits in model learning. Through a deep analysis of the task-recency bias caused by class imbalance, we propose a revised focal loss to mainly keep stability. \Rt{By utilizing a new weight function, the revised focal loss will pay more attention to current ambiguous samples, which are the potentially valuable samples to make model progress quickly.} To promote plasticity, we introduce a virtual knowledge distillation. By designing a virtual teacher, it assigns more attention to non-target classes, which can surmount overconfidence and encourage model to focus on inter-class information. Extensive experiments on three popular datasets for OCIL have shown the effectiveness of AFS. The code will be available at \url{https://github.com/czjghost/AFS}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
