Mixture of Mixups for Multi-label Classification of Rare Anuran Sounds - Equipe Better Representations for Artificial Intelligence Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Mixture of Mixups for Multi-label Classification of Rare Anuran Sounds

Résumé

Multi-label imbalanced classification poses a significant challenge in machine learning, particularly evident in bioacoustics where animal sounds often co-occur, and certain sounds are much less frequent than others. This paper focuses on the specific case of classifying anuran species sounds using the dataset AnuraSet, that contains both class imbalance and multi-label examples. To address these challenges, we introduce Mixture of Mixups (Mix2), a framework that leverages mixing regularization methods Mixup, Manifold Mixup, and MultiMix. Experimental results show that these methods, individually, may lead to suboptimal results; however, when applied randomly, with one selected at each training iteration, they prove effective in addressing the mentioned challenges, particularly for rare classes with few occurrences. Further analysis reveals that the model trained using Mix2 is also proficient in classifying sounds across various levels of class co-occurrences.
Fichier principal
Vignette du fichier
Mix2___EUSIPCO_2024_Submission-1.pdf (389.47 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04620733 , version 1 (21-06-2024)

Licence

Identifiants

  • HAL Id : hal-04620733 , version 1

Citer

Ilyass Moummad, Nicolas Farrugia, Romain Serizel, Jeremy Froidevaux, Vincent Lostanlen. Mixture of Mixups for Multi-label Classification of Rare Anuran Sounds. EUSIPCO 2024, Aug 2024, Lyon, France. ⟨hal-04620733⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More