Dual-CBA：从双层优化视角通过双重持续偏置适配器改进在线持续学习
Dual-CBA: Improving Online Continual Learning via Dual Continual Bias Adaptors from a Bi-level Optimization Perspective
AI总结：
本文提出Dual-CBA框架，通过结合类别特定与类别无关的持续偏置适配器及增量批归一化模块，从双层优化视角有效缓解在线持续学习中的灾难性遗忘与分布偏移问题。
摘要：
在在线持续学习（CL）中，基于变化分布训练的模型很容易遗忘先前学习的知识，并偏向新接收的任务。为了解决这个问题，我们提出了持续偏置适配器（CBA），这是一个双层框架，它增强了分类网络以在训练期间适应灾难性的分布偏移，使网络能够实现对所有已见任务的稳定巩固。然而，CBA模块以特定类别的方式调整分布偏移，加剧了稳定性差距问题，并在某种程度上无法满足在线CL中持续测试的需求。为了缓解这一挑战，我们进一步提出了一种新颖的类别无关CBA模块，该模块分别聚合来自新任务和旧任务的类别的后验概率，并对所得的后验概率应用稳定的调整。我们将这两种CBA模块组合成一个统一的Dual-CBA模块，从而能够适应灾难性的分布偏移，并同时满足在线CL的实时测试要求。此外，我们提出了增量批归一化（IBN），这是一个定制的BN模块，用于重新估计其总体统计量，以缓解由我们双层框架的内循环优化问题引起的特征偏置。为了验证所提方法的有效性，我们从理论上提供了一些关于它如何缓解灾难性分布偏移的见解，并通过基于四个基于重放的基线和三个公共持续学习基准的广泛实验，实证证明了其优越性。
英文摘要：
In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level framework that augments the classification network to adapt to catastrophic distribution shifts during training, enabling the network to achieve a stable consolidation of all seen tasks. However, the CBA module adjusts distribution shifts in a class-specific manner, exacerbating the stability gap issue and, to some extent, fails to meet the need for continual testing in online CL. To mitigate this challenge, we further propose a novel class-agnostic CBA module that separately aggregates the posterior probabilities of classes from new and old tasks, and applies a stable adjustment to the resulting posterior probabilities. We combine the two kinds of CBA modules into a unified Dual-CBA module, which thus is capable of adapting to catastrophic distribution shifts and simultaneously meets the real-time testing requirements of online CL. Besides, we propose Incremental Batch Normalization (IBN), a tailored BN module to re-estimate its population statistics for alleviating the feature bias arising from the inner loop optimization problem of our bi-level framework. To validate the effectiveness of the proposed method, we theoretically provide some insights into how it mitigates catastrophic distribution shifts, and empirically demonstrate its superiority through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.
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。
