Papers
arxiv:2007.16187

Ultra-light deep MIR by trimming lottery tickets

Published on Jul 31, 2020
Authors:
,
,
,
,

Abstract

Deep learning models for music information retrieval can be significantly compressed through structured pruning while maintaining accuracy and enabling deployment on resource-constrained devices.

Current state-of-the-art results in Music Information Retrieval are largely dominated by deep learning approaches. These provide unprecedented accuracy across all tasks. However, the consistently overlooked downside of these models is their stunningly massive complexity, which seems concomitantly crucial to their success. In this paper, we address this issue by proposing a model pruning method based on the lottery ticket hypothesis. We modify the original approach to allow for explicitly removing parameters, through structured trimming of entire units, instead of simply masking individual weights. This leads to models which are effectively lighter in terms of size, memory and number of operations. We show that our proposal can remove up to 90% of the model parameters without loss of accuracy, leading to ultra-light deep MIR models. We confirm the surprising result that, at smaller compression ratios (removing up to 85% of a network), lighter models consistently outperform their heavier counterparts. We exhibit these results on a large array of MIR tasks including audio classification, pitch recognition, chord extraction, drum transcription and onset estimation. The resulting ultra-light deep learning models for MIR can run on CPU, and can even fit on embedded devices with minimal degradation of accuracy.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2007.16187 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2007.16187 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2007.16187 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.