提出新损失函数，让音频分类的特征更区分且无层级
Angular Distance Distribution Loss for Audio Classification
- 基于角度距离分布，同时优化类内/类间距离和层级关系
- 在AudioSet等数据集上显著提升分类准确率
- 适合需要高质量特征表示的音频识别任务
分类是深度学习中的核心任务，不仅因其自身重要性，还因为它能为其他任务生成具有良好性质的嵌入表示。为优化这些性质，已有大量损失函数被提出，旨在最小化类内距离并最大化类间距离。本文认为，除了上述两点外，消除类内与类间的层级结构也是分类嵌入的可取属性。为此，我们提出角距离分布（ADD）损失，通过施加嵌入角度距离的一阶与二阶统计矩约束，联合增强这四项性质。实验表明，该损失函数在多个音频分类任务中均优于现有方法，全面提升了分类性能。
原文摘要 · Abstract (English)
Classification is a pivotal task in deep learning not only because of its intrinsic importance, but also for providing embeddings with desirable properties in other tasks. To optimize these properties, a wide variety of loss functions have been proposed that attempt to minimize the intra-class distance and maximize the inter-class distance in the embeddings space. In this paper we argue that, in addition to these two, eliminating hierarchies within and among classes are two other desirable properties for classification embeddings. Furthermore, we propose the Angular Distance Distribution (ADD) Loss, which aims to enhance the four previous properties jointly. For this purpose, it imposes conditions on the first and second order statistical moments of the angular distance between embeddings. Finally, we perform experiments showing that our loss function improves all four properties and, consequently, performs better than other loss functions in audio classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。