Supervised contrastive learning for pre-training bioacoustic few-shot systems - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 2023

Supervised contrastive learning for pre-training bioacoustic few-shot systems

Abstract

We show in this work that learning a rich feature extractor from scratch using only official training data is feasible. We achieve this by learning representations using a supervised contrastive learning framework. We then transfer the learned feature extractor to the sets of validation and test for few-shot evaluation. For fewshot validation, we simply train a linear classifier on the negative and positive shots and obtain a F-score of 63.46% outperforming the baseline by a large margin. We don't use any external data or pretrained model. Our approach doesn't require choosing a threshold for prediction or any post-processing technique. Our code is publicly available on Github : https://github.com/ ilyassmoummad/dcase23_task5_scl
Fichier principal
Vignette du fichier
DCASE2023_Moummad_IMT_t5 (1).pdf (182.31 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04165306 , version 1 (25-07-2023)

Licence

Identifiers

  • HAL Id : hal-04165306 , version 1

Cite

Ilyass Moummad, Romain Serizel, Nicolas Farrugia. Supervised contrastive learning for pre-training bioacoustic few-shot systems. IMT Atlantique; LORIA. 2023. ⟨hal-04165306⟩
82 View
93 Download

Share

Gmail Mastodon Facebook X LinkedIn More