Metric Learning Vs Classification For Disentangled Music Representation Learning

Abstract

Deep representation learning offers a powerful paradigm for mapping input data onto an organized embedding space and is useful for many music information retrieval tasks. Two central methods for representation learning include deep metric learning and classification, both having the same goal of learning a representation that can generalize well across tasks. Along with generalization, the emerging concept of disentangled representations is also of great interest, where multiple semantic concepts (e.g., genre, mood, instrumentation) are learned jointly but remain separable in the learned representation space. In this paper we present a single representation learning framework that elucidates the relationship between metric learning, classification, and disentanglement in a holistic manner. For this, we (1) outline past work on the relationship between metric learning and classification, (2) extend this relationship to multi-label data by exploring three different learning approaches an

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylee2020metric

Related papers

• Disentangled Multidimensional Metric Learning For Music Similarity (2020)10.61
• Multimodal Metric Learning For Tag-based Music Retrieval (2020)9.76
• Exploring Modality-agnostic Representations For Music Classification (2021)0.00
• Representation Learning For Image-based Music Recommendation (2018)0.00
• Self-supervised Auxiliary Loss For Metric Learning In Music Similarity-based Retrieval And Auto-tagging (2023)0.00
• Classification Is A Strong Baseline For Deep Metric Learning (2018)0.00
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Metric Learning As A Service With Covariance Embedding (2022)3.58