An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging

arXiv:2404.09177v1 Announce Type: cross
Abstract: Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming, error-prone, and ambiguous. During the self-supervised process, models are trained on pretext tasks, with the primary objective of acquiring robust and informative features that can later be fine-tuned for specific downstream tasks. The choice of the pretext task is critical as …

abstract arxiv comparison cs.lg cs.sd data domain eess.as error experimental machine machine learning machine learning models music process self-supervised learning supervised learning tagging train type view