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%.

翻译：本文针对解决序列化多标签音频分类任务中潜在重叠声音类别的类增量学习问题，提出一种新方法。我们设计了一种独立于旧类别学习新类别的增量学习器。为保持旧类别知识，提出基于余弦相似度的蒸馏损失函数，通过最小化后续学习器特征表示差异保留知识，同时结合基于Kullback-Leibler散度的蒸馏损失函数，最小化两者输出分布的差异。实验采用包含50个声音类别的数据集，初始分类任务含30个基类，后续分4个增量阶段各新增5个类别。每个阶段后，系统需对当前已学全部类别进行多标签分类测试。所提方法在五个阶段上的平均F1得分为40.9%，范围从阶段0（30类）的45.2%下降至阶段4（50类）的36.3%。相比初始F1得分45.2%，增量阶段平均性能衰减仅为0.7个百分点。