Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis - Laboratoire Traitement et Communication de l'Information Access content directly
Conference Papers Year : 2023

Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis

Abstract

We introduce Resilient Multiple Choice Learning (rMCL), an extension of the MCL approach for conditional distribution estimation in regression settings where multiple targets may be sampled for each training input. Multiple Choice Learning is a simple framework to tackle multimodal density estimation, using the Winner-Takes-All (WTA) loss for a set of hypotheses. In regression settings, the existing MCL variants focus on merging the hypotheses, thereby eventually sacrificing the diversity of the predictions. In contrast, our method relies on a novel learned scoring scheme underpinned by a mathematical framework based on Voronoi tessellations of the output space, from which we can derive a probabilistic interpretation. After empirically validating rMCL with experiments on synthetic data, we further assess its merits on the sound source localization problem, demonstrating its practical usefulness and the relevance of its interpretation.
Fichier principal
Vignette du fichier
neurips_2023.pdf (1.64 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
licence : CC BY NC ND - Attribution - NonCommercial - NoDerivatives

Dates and versions

hal-04216055 , version 1 (31-10-2023)

Identifiers

  • HAL Id : hal-04216055 , version 1

Cite

Victor Letzelter, Mathieu Fontaine, Mickaël Chen, Patrick Pérez, Slim Essid, et al.. Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis. Advances in neural information processing systems, Dec 2023, New Orleans, United States. ⟨hal-04216055⟩
219 View
22 Download

Share

Gmail Facebook X LinkedIn More