English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep representation learning offers a powerful paradigm for mapping inputdata onto an organized embedding space and is useful for many music informationretrieval tasks. Two central methods for representation learning include deepmetric learning and classification, both having the same goal of learning arepresentation that can generalize well across tasks. Along withgeneralization, the emerging concept of disentangled representations is also ofgreat interest, where multiple semantic concepts (e.g., genre, mood,instrumentation) are learned jointly but remain separable in the learnedrepresentation space. In this paper we present a single representation learningframework 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 andclassification, (2) extend this relationship to multi-label data by exploringthree different learning approaches and their disentangled versions, and (3)evaluate all models on four tasks (training time, similarity retrieval,auto-tagging, and triplet prediction). We find that classification-based modelsare generally advantageous for training time, similarity retrieval, andauto-tagging, while deep metric learning exhibits better performance fortriplet-prediction. Finally, we show that our proposed approach yieldsstate-of-the-art results for music auto-tagging.

Metric Learning vs Classification for Disentangled Music Representation Learning