arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.04447eess.AScs.SD
收藏

多标签音频分类的类增量学习

Class-Incremental Learning for Multi-Label Audio Classification

Tampere University(坦佩雷大学)

Manjunath Mulimani, Annamaria Mesaros

AI总结:

本文提出一种多标签音频分类的类增量学习方法,结合基于余弦相似度和Kullback-Leibler散度的蒸馏损失保留旧类知识,在50类数据集上平均F1分数达40.9%,性能下降仅0.7个百分点。

摘要:

本文提出一种针对潜在重叠声音的类增量学习方法,用于解决一系列多标签音频分类任务。我们设计了一个独立于旧类学习新类的增量学习器。为保留旧类知识,我们提出一种基于余弦相似度的蒸馏损失以最小化后续学习器特征表示的差异,并将其与基于Kullback-Leibler散度的蒸馏损失结合使用,以最小化各自输出的差异。实验在一个包含50个声音类的数据集上进行,初始分类任务包含30个基类,随后是4个增量阶段,每阶段5个类。每阶段后,系统均使用迄今学到的全部类别进行多标签分类测试。所提方法在五个阶段中获得了40.9%的平均F1分数,从阶段0的30个类的45.2%到阶段4的50个类的36.3%。相对于初始45.2%的F1分数,增量阶段的平均性能下降仅为0.7个百分点。

英文摘要:

In this paper, we propose a method for class-incremental learning of potentially overlapping sounds for solving a sequence of multi-label audio classification tasks. We design an incremental learner that learns new classes independently of the old classes. To preserve knowledge about the old classes, we propose a cosine similarity-based distillation loss that minimizes discrepancy in the feature representations of subsequent learners, and use it along with a Kullback-Leibler divergence-based distillation loss that minimizes discrepancy in their respective outputs. Experiments are performed on a dataset with 50 sound classes, with an initial classification task containing 30 base classes and 4 incremental phases of 5 classes each. After each phase, the system is tested for multi-label classification with the entire set of classes learned so far. The proposed method obtains an average F1-score of 40.9% over the five phases, ranging from 45.2% in phase 0 on 30 classes, to 36.3% in phase 4 on 50 classes. Average performance degradation over incremental phases is only 0.7 percentage points from the initial F1-score of 45.2%.

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。

↑