在线多功能增量学习：面向任意时间的类别与领域无关自适应
Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time
- Korea University（高丽大学）
- Kyung Hee University（庆熙大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对类别和领域同时在线演变的持续学习难题，提出TopFlow框架，通过领域无关流匹配和全局拓扑保持机制，在无明确边界场景下实现最先进性能。
AI中文摘要：
持续学习使视觉系统能够适应不断变化的数据分布。尽管取得了显著进展，现有方法未能捕捉类别和领域的连续且并发变化，而这对于现实世界部署至关重要。这项工作引入了在线多功能增量学习（Online VIL），这是一种新颖的场景，其中类别概念和视觉领域在没有明确边界的情况下同时在线演变。为了更好地适应这些更接近现实世界条件的动态环境所带来的挑战，我们提出了一种新颖框架TopFlow，即拓扑保持与流匹配表示，它包含两种互补机制：领域无关流匹配（DFM）和全局拓扑保持（GTP）。DFM通过将测地线流核整合到对比学习中，引导模型具有领域无关的表示。相比之下，GTP在不显式存储过去示例的情况下维护特征空间的全局结构。我们的大量实验表明，TopFlow有效解决了现有方法在在线VIL场景中的局限性，在具有挑战性的在线VIL中实现了最先进的性能。所提出的方法为在现实动态环境中构建持续学习系统指明了潜在方向。我们的实现代码可在以下https URL获取。
英文摘要：
Continual learning enables vision systems to adapt to ever-changing data distributions. Despite significant advances, existing approaches fail to capture continuous and concurrent shifts in classes and domains, a critical capability for real-world deployment. This work introduces Online VIL (Online Versatile Incremental Learning), a novel scenario where class concepts and visual domains evolve simultaneously online without explicit boundaries. To better adapt to the challenges of such dynamic environments that more closely resemble real-world conditions, we propose a novel framework TopFlow, Topology preservation with Flow matching representation that contains two complementary mechanisms: Domain-agnostic Flow Matching (DFM) and Global Topology Preservation (GTP). DFM guides the model to have domain-agnostic representations by integrating the geodesic flow kernel into contrastive learning. In contrast, GTP maintains the global structure of the feature space without explicitly storing past examples. Our extensive experiments demonstrate that TopFlow effectively addresses the limitations of existing methods within the Online VIL scenario, achieving state-of-the-art performance in challenging Online VIL. The proposed methods suggest potential directions for building continual learning systems in realistic dynamic environments. Our implementation code is available at https://github.com/KU-VGI/Online-VIL.
