论文标题
使用角对比度损失对音频表示的自我监督学习
Self-supervised learning of audio representations using angular contrastive loss
论文作者
论文摘要
在自我监督的学习（SSL）中，各种借口任务都是为了通过对比损失而设计的。但是，先前的研究表明，由于实例歧视目标的固有缺陷，这种损失对语义相似的样本的耐受性较低，这可能会损害下游任务中使用的学习特征嵌入的质量。为了提高SSL中特征嵌入的歧视能力，我们提出了一种称为角对比度损失（ACL）的新损失函数，即角缘和对比度损耗的线性组合。 ACL通过在SSL中的正和负增强对之间显式添加角缘来改善对比度学习。实验结果表明，使用ACL进行监督和无监督学习可以显着提高性能。我们使用FSDNOISY18K数据集验证了我们的新损失函数，在该数据集中，我们在声音事件分类中分别使用受监督和自我监督的学习在声音事件分类中获得了73.6％和77.1％的精度。
In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically similar samples due to the inherent defect of instance discrimination objectives, which may harm the quality of learned feature embeddings used in downstream tasks. To improve the discriminative ability of feature embeddings in SSL, we propose a new loss function called Angular Contrastive Loss (ACL), a linear combination of angular margin and contrastive loss. ACL improves contrastive learning by explicitly adding an angular margin between positive and negative augmented pairs in SSL. Experimental results show that using ACL for both supervised and unsupervised learning significantly improves performance. We validated our new loss function using the FSDnoisy18k dataset, where we achieved 73.6% and 77.1% accuracy in sound event classification using supervised and self-supervised learning, respectively.
