{"ID":5935749,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-11T07:13:06.997309296Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03304","arxiv_id":"2607.03304","title":"Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types","abstract":"Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets. We extend BirdCallNet for joint species and call-type classification on the long-tailed WiWa dataset and investigate how task-loss balancing interacts with pretrained representations and adaptation depth. We evaluate four bird-domain encoders, ConvNeXtBS, EAT, BirdMAE, and ProtoCLR, with separate species and call-type heads under linear probing, attentive probing, and full fine-tuning. A manually tuned fixed objective is compared with homoscedastic uncertainty weighting and Dynamic Weight Averaging across all three adaptation regimes, while GradNorm is evaluated only under full fine-tuning. Results indicate that the factorised multi-task formulation yields the most consistent improvements over the combined single-task baseline for call-type recognition, while its effect on species recognition depends on the adaptation regime. Full fine-tuning is not consistently optimal: ConvNeXtBS achieves the highest mean species performance under linear probing, whereas BirdMAE provides the strongest call-type performance under attentive probing. Adaptive weighting benefits species recognition more consistently than call-type recognition. Uncertainty weighting is particularly effective for species recognition under attentive probing, whereas Dynamic Weight Averaging is generally stronger for the same task under full fine-tuning. GradNorm achieves competitive call-type performance for selected backbones but consistently underperforms other weighting strategies for species recognition and incurs higher computational and memory costs. Overall, the preferred loss-balancing strategy depends on the backbone, adaptation regime, and target task, while frozen-backbone adaptation can provide a more favourable performance-efficiency trade-off than end-to-end fine-tuning.","short_abstract":"Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets. We extend BirdCallNet for joint species and call-type classification on the long-tailed WiWa dataset and investigate how task-loss balancing interacts with pretrained representations...","url_abs":"https://arxiv.org/abs/2607.03304v1","url_pdf":"https://arxiv.org/pdf/2607.03304v1","authors":"Paria Vali Zadeh, Sven Tomforde","published":"2026-07-03T13:16:30Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.LG\",\"eess.AS\",\"q-bio.QM\"]","methods":"[]","has_code":false}