Dual-Estimator：解耦全局与局部语义漂移以补偿类增量学习中的漂移
Dual-Estimator: Decoupling Global and Local Semantic Shift for Drift Compensation in Class-Incremental Learning
对做类增量视觉分类的人，这篇给出了一个可直接插拔的漂移补偿模块：用混合专家估计器建模任务内非均匀语义分布、用低秩估计器捕捉任务间非均匀漂移，且以解析解在少数 epoch 内更新，可挂到现有 exemplar-free 方法上缓解旧类表征失活。
原文依据 Dual-E leverages analytical solutions to update within a few epochs, enabling efficient plug-in integration with existing exemplar-free methods.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论持续学习（CL）为获取新知识提供了一种有效范式，而无需保留过去样本的原则催生了更贴合实际条件的无样本持续学习。然而，一个关键挑战是语义漂移，它要求可靠地激活过去类别的表征以与当前特征空间对齐。漂移补偿充当了这种激活器，但它通常假设语义分布与漂移是均匀的，这对于随机数据流并不现实。为此，我们提出 Dual-Estimator（Dual-E）来解耦全局与局部语义漂移，从而同时应对上述两种非均匀性问题。具体而言，针对任务内非均匀语义分布限制了低频语义的有效补偿这一问题，Dual-E 引入由多个网络组成的混合专家估计器，在不同局部表征空间中建模语义漂移。针对语义漂移在任务间的非均匀性——即均匀的全尺度补偿可能忽略各类别间语义变化程度的差异——Dual-E 采用带有内嵌低秩网络的低秩估计器，对漂移较大的类别优先关注全局语义趋势。Dual-E 利用解析解在少数几个 epoch 内完成更新，从而能够高效地即插即用地集成到现有无样本方法中。在多个数据集上的大量实验证明了 Dual-E 优于最优方法。
英文原文摘要 1518 字符
Continual Learning (CL) provides an effective paradigm for acquiring new knowledge, and the principle of learning without retaining past samples has led to exemplar-free CL that better matches practical conditions. However, a key challenge is the semantic shift, which requires reliable activation of past class representations to align with the current feature space. While drift compensation acts as the activator, it commonly assumes uniform semantic distributions and shifts, which is unrealistic for random data streams. For this, we propose the Dual-Estimator (Dual-E) to decouple global and local semantic shifts, addressing both issues of non-uniformity. Specifically, to address intra-task non-uniform semantic distributions that limit effective compensation for low-frequency semantics, Dual-E incorporates a mixture-of-experts estimator comprising multiple networks that model semantic shifts across diverse local representation spaces. For inter-task non-uniformity in semantic shifts, where uniform full-scale compensation potentially overlooks the varying degrees of semantic change across classes, Dual-E employs a low-rank estimator with an embedded low-rank network that prioritizes global semantic trends for classes exhibiting larger shifts. Dual-E leverages analytical solutions to update within a few epochs, enabling efficient plug-in integration with existing exemplar-free methods. Extensive experiments on diverse datasets demonstrate the advantages of Dual-E over state-of-the-art approaches.