渐进式保守适应用于演化目标域
Progressive Conservative Adaptation for Evolving Target Domains
AI总结：
针对目标域持续演化的问题，提出渐进式保守适应方法，利用类原型微调分类器并采用保守稀疏注意力保护历史知识，在多个数据集上验证了有效性。
摘要：
传统的域适应通常将知识从源域迁移到一个静态的目标域。然而，在许多现实场景中，目标数据通常按顺序出现，且分布持续演化。恢复并适应此类目标数据会导致计算和资源消耗随时间不断攀升。因此，设计算法来解决演化域适应（EDA）问题至关重要，即在无法访问历史目标域的情况下，使模型适应不断演化的目标域。为实现这一目标，我们提出了一种简单而有效的方法，称为渐进式保守适应（PCAda）。为了处理与先前分布不同的新目标数据，我们基于逐步更新的类原型对分类器头部进行微调。此外，由于适应最近的目标域可能会干扰从先前目标域学到的特征，我们开发了一种保守稀疏注意力机制。该机制将特征适应限制在必要的维度内，从而减轻与历史知识相关的推理负担。所提出的PCAda通过元学习框架实现，在内循环中借助逐步更新的类原型实现分类器的快速适应，在外循环中通过保守稀疏注意力学习泛化特征，同时不严重干扰历史知识。在Rotated MNIST、Caltran和Portraits数据集上的实验证明了我们方法的有效性。
英文摘要：
Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. However, in many real-world cases, target data usually emerge sequentially and have continuously evolving distributions. Restoring and adapting to such target data results in escalating computational and resource consumption over time. Hence, it is vital to devise algorithms to address the evolving domain adaptation (EDA) problem, \emph{i.e.,} adapting models to evolving target domains without access to historic target domains. To achieve this goal, we propose a simple yet effective approach, termed progressive conservative adaptation (PCAda). To manage new target data that diverges from previous distributions, we fine-tune the classifier head based on the progressively updated class prototypes. Moreover, as adjusting to the most recent target domain can interfere with the features learned from previous target domains, we develop a conservative sparse attention mechanism. This mechanism restricts feature adaptation within essential dimensions, thus easing the inference related to historical knowledge. The proposed PCAda is implemented with a meta-learning framework, which achieves the fast adaptation of the classifier with the help of the progressively updated class prototypes in the inner loop and learns a generalized feature without severely interfering with the historic knowledge via the conservative sparse attention in the outer loop. Experiments on Rotated MNIST, Caltran, and Portraits datasets demonstrate the effectiveness of our method.
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。
