几何锚定传输框架用于无样本类增量学习
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
AI总结：
提出几何锚定传输框架，通过分析几何锚定和拓扑感知演化约束，在训练阶段内嵌特征传输，解决无样本类增量学习中的各向异性漂移问题。
摘要：
无样本类增量学习（EFCIL）需要在不断变化的特征空间中保持稳定的决策边界。虽然维护类别条件高斯统计量提供了一种原则性的分类策略，但这些参数化摘要仍然对各向异性表示漂移敏感。现有方法通常采用解耦的后处理范式跨任务传输这些统计量：优化骨干网络时缺乏显式几何约束会扭曲旧流形，限制回溯对齐的精度。在本文中，我们将特征传输形式化为内生训练约束而非单独的后任务步骤，提出了几何锚定传输框架。首先，我们通过马氏对齐回归推导出分析几何锚定，以缓解宏观各向异性漂移。其次，我们引入拓扑感知演化目标，在根据分析先验校准残差网络的同时正则化局部流形退化。通过在主要训练阶段将流形演化与传输约束耦合，我们的框架无需解耦微调即可减少评估误差。在CIFAR-100、TinyImageNet和ImageNet-100上的实验表明，在严格的无样本约束下，所提框架一致优于现有的后处理替代方法。
英文摘要：
Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditional Gaussian statistics provides a principled classification strategy, these parametric summaries remain sensitive to anisotropic representation drift. Existing methods often transport these statistics across tasks using a decoupled, post-hoc paradigm: optimizing a backbone without explicit geometric constraints can distort the legacy manifold, limiting the precision of retroactive alignment. In this paper, we formulate feature transport as an endogenous training constraint rather than a separate post-task step, presenting the Geometry-Anchored Transport Framework. First, we derive an Analytic Geometric Anchor via Mahalanobis-aligned regression to mitigate macroscopic anisotropic drift. Second, we introduce a Topology-Aware Evolution objective that regularizes localized manifold degradation while calibrating a residual network against the analytic prior. By coupling manifold evolution with transport constraints during the primary training phase, our framework mitigates evaluation errors without requiring decoupled fine-tuning. Experiments across CIFAR-100, TinyImageNet, and ImageNet-100 demonstrate that the proposed framework consistently improves upon existing post-hoc alternatives under strict exemplar-free constraints.
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。
