一种最优传输驱动的在线增量学习潜空间培育方法
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
把最优传输驱动的在线混合模型用于潜空间中类别中心的增量演化，替代单一或固定多中心表示，可直接迁移到视觉模型的类增量/在线持续学习场景，缓解多模态数据流下的灾难性遗忘。
原文依据 we introduce an online Mixture Model learning framework grounded in Optimal Transport theory (MMOT), where centroids evolve incrementally with new data
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在在线增量学习中，数据持续到达且伴随显著的分布偏移，由于无法回访先前样本，这构成了重大挑战。已有研究通常依赖单一自适应中心或固定的多中心来在潜空间中表示每个类别。然而，当类别数据流本身具有多模态性且需要持续更新中心时，这类方法难以奏效。为克服这一问题，我们提出一种基于最优传输理论的在线混合模型学习框架（MMOT），其中中心随新数据增量演化。该方法具有两大优势：(i) 它能更精确地刻画复杂数据流；(ii) 它借助 MMOT 导出的中心，在推理阶段能对未见样本实现更优的类别相似度估计。此外，为强化表征学习并缓解灾难性遗忘，我们设计了一种动态保持策略，用于调控潜空间并在时间推移中维持类别可分性。在基准数据集上的实验评估证实了所提方法的优越有效性。
英文原文摘要 1166 字符
In online incremental learning, data continuously arrives with substantial shifts in distribution, creating a significant challenge since previous samples cannot be revisited. Prior research has typically relied on either a single adaptive centroid or fixed multiple centroids to represent each class in the latent space. However, such methods struggle when class data streams are inherently multimodal and require continual centroid updates. To overcome this, we introduce an online Mixture Model learning framework grounded in Optimal Transport theory (MMOT), where centroids evolve incrementally with new data. This approach offers two main advantages: (i) it provides a more precise characterization of complex data streams, and (ii) it enables improved class similarity estimation for unseen samples during inference through MMOT-derived centroids. Furthermore, to strengthen representation learning and mitigate catastrophic forgetting, we design a Dynamic Preservation strategy that regulates the latent space and maintains class separability over time. Experimental evaluations on benchmark datasets confirm the superior effectiveness of our proposed method.