BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics

Jenny Hamer, Eleni Triantafillou, Bart van Merriënboer, Stefan Kahl, Holger Klinck, tom denton, Vincent Dumoulin

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: benchmark, generalization, retrieval, bioacoustics

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A holistic, robust retrieval benchmark for evaluating models' ability to generalize within the context of a collection of rich bioacoustics tasks.

Abstract: The ability for a machine learning model to cope with differences in training and deployment conditions—e.g. in the presence of distribution shift or the generalization to new classes altogether—is crucial for real-world use cases. However, most empirical work in this area has focused on the image domain with artificial benchmarks constructed to measure individual aspects of generalization. We present BIRB, a complex benchmark centered on the retrieval of bird vocalizations from passively-recorded datasets given focal recordings from a large citizen science corpus available for training. We propose a baseline system for this collection of tasks using representation learning and a nearest-centroid search. Our thorough empirical evaluation and analysis surfaces open research directions, suggesting that BIRB fills the need for a more realistic and complex benchmark to drive progress on robustness to distribution shifts and generalization of ML models.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6091