Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning - Signaux et Images Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning

Résumé

Multi-label audio tagging consists of assigning sets of tags to audio recordings. At inference time, thresholds are applied on the confidence scores outputted by a probabilistic classifier, in order to decide which classes are detected active. In this work, we consider having at disposal a trained classifier and we seek to automatically optimize the decision thresholds according to a performance metric of interest, in our case F-measure (micro-F1). We propose a new method, called SGL-Thresh for Surrogate Gradient Learning of Thresholds, that makes use of gradient descent. Since F1 is not differentiable, we propose to approximate the thresholding operation gradients with the gradients of a sigmoid function. We report experiments on three datasets, using state-of-the-art pre-trained deep neural networks. In all cases, SGL-Thresh outperformed three other approaches: a default threshold value (defThresh), an heuristic search algorithm and a method estimating F1 gradients numerically. It reached 54.9\% F1 on AudioSet eval, compared to 50.7% with defThresh. SGL-Thresh is very fast and scalable to a large number of tags. To facilitate reproducibility, data and source code in Pytorch are available online: https://github.com/topel/SGL-Thresh
Fichier principal
Vignette du fichier
ICASSP_2021_seuils.pdf (117.51 Ko) Télécharger le fichier
main_icassp2021.pdf (80.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03153644 , version 1 (26-02-2021)

Identifiants

Citer

Thomas Pellegrini, Timothée Masquelier. Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning. IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2021, Toronto, Canada. pp. 651-655, ⟨10.1109/ICASSP39728.2021.9414091⟩. ⟨hal-03153644⟩
187 Consultations
126 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More