无样本解析学习用于多标签音频类增量学习
Exemplar-Free Analytic Learning for Multi-Label Audio Class-Incremental Learning
- The University of Melbourne（墨尔本大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出ALMA，一种基于无样本解析学习的多标签音频类增量学习方法，通过闭式更新线性分类器并利用旧类分数估计与频率加权，在AudioSet-R基准上显著优于梯度方法且不遗忘旧类。
AI中文摘要：
音频分类本质上是一个多标签任务，因为真实世界的声学环境包含多个同时发生的声音事件。当新的声音类别出现时，模型必须在不遗忘先前学习类别的情况下将其纳入，这一挑战被称为类增量学习。现有方法依赖存储过去的数据和迭代梯度更新，在不完全多标签监督下难以奏效，因为每个阶段仅标注新引入的类别，旧类别标签不可用。我们研究无样本解析持续学习作为一种原则性替代方案，其中线性分类器以闭式更新，无需存储历史录音或执行增量反向传播，且先前学习的权重在构造上保持不变。基于解析学习，我们进一步提出ALMA，通过连续旧类别分数估计和基于频率的样本加权来解决不完全监督和类别不平衡问题。在50类AudioSet-R基准上的三个增量设置实验中，解析学习器显著优于基于梯度的方法，且随着新类别的加入，先前学习的类别检测性能几乎保持不变。本研究表明，ALMA是多标签音频类增量学习的一种简单而有效的解决方案。
英文摘要：
Audio classification is inherently a multi-label task, as real-world acoustic environments contain multiple simultaneous sound events. When new sound classes emerge, models must incorporate them without forgetting previously learned ones: a challenge known as class-incremental learning. Existing methods rely on storing past data and iterative gradient updates, which struggle under incomplete multi-label supervision because only the newly introduced classes are annotated at each phase, leaving old-class labels unavailable. We investigate exemplar-free analytic continual learning as a principled alternative, in which a linear classifier is updated in closed form without storing historical recordings or performing incremental back-propagation, and previously learned weights remain intact by construction. Building on analytic learning, we further propose ALMA, which addresses incomplete supervision and class imbalance through continuous old-class score estimates and frequency-based sample weighting. Experiments on a 50-class AudioSet-R benchmark across three incremental setups show that the analytic learner substantially outperforms gradient-based methods, and previously learned classes retain nearly unchanged detection performance as new classes are added. This study shows that ALMA is a simple yet effective solution to multi-label audio class-incremental learning.
