Transfer Learning with Pseudo Multi-Label Birdcall Classification for DS@GT BirdCLEF 2024

TL;DR

This paper discusses transfer learning with pseudo multi-label classification for birdcall identification in the BirdCLEF 2024 challenge, utilizing advanced models and addressing data distribution challenges to improve species recognition accuracy.

Contribution

It introduces a pseudo multi-label classification strategy leveraging unlabeled data and advanced models like BirdNET and EnCodec for birdcall classification.

Findings

Achieved a top leaderboard score of 0.63 with BirdNET embeddings.

Utilized pseudo-labeling to address distributional shift in unlabeled soundscape data.

Demonstrated the effectiveness of transfer learning in birdcall classification.

Abstract

We present working notes for the DS@GT team on transfer learning with pseudo multi-label birdcall classification for the BirdCLEF 2024 competition, focused on identifying Indian bird species in recorded soundscapes. Our approach utilizes production-grade models such as the Google Bird Vocalization Classifier, BirdNET, and EnCodec to address representation and labeling challenges in the competition. We explore the distributional shift between this year's edition of unlabeled soundscapes representative of the hidden test set and propose a pseudo multi-label classification strategy to leverage the unlabeled data. Our highest post-competition public leaderboard score is 0.63 using BirdNET embeddings with Bird Vocalization pseudo-labels. Our code is available at https://github.com/dsgt-kaggle-clef/birdclef-2024