Masked Autoencoders (MAEs) pretrained on AudioSet fail to capture the fine-grained acoustic characteristics of specialized domains such as bioacoustic monitoring. Bird sound classification is critical for assessing environmental health, yet general-purpose models inadequately address its unique acoustic challenges. To address this, we introduce Bird-MAE, a domain-specialized MAE pretrained on the large-scale BirdSet dataset. We explore adjustments to pretraining, fine-tuning and utilizing frozen representations. Bird-MAE achieves state-of-the-art results across all BirdSet downstream tasks, substantially improving multi-label classification performance compared to the general-purpose Audio-MAE baseline. Additionally, we propose prototypical probing, a parameter-efficient method for leveraging MAEs' frozen representations. Bird-MAE's prototypical probes outperform linear probing by up to 37\% in MAP and narrow the gap to fine-tuning to approximately 3\% on average on BirdSet.
View on arXiv@article{rauch2025_2504.12880,
title={ Can Masked Autoencoders Also Listen to Birds? },
author={ Lukas Rauch and Ilyass Moummad and René Heinrich and Alexis Joly and Bernhard Sick and Christoph Scholz },
journal={arXiv preprint arXiv:2504.12880},
year={ 2025 }
}