Publication
Leveraging Weakly Supervised and Multiple Instance Learning for Multi-label Classification of Passive Acoustic Monitoring Data
Ilira Troshani; Thiago Gouvea; Daniel Sonntag
In: KI 2024: Advances in Artificial Intelligence. German Conference on Artificial Intelligence (KI-2024), 47th German Conference on AI, Würzburg, Germany, September 25–27, 2023, located at 47th German Conference on AI, September 25-27, Würzburg, Germany, LNAI, Springer, 2024.
Abstract
Data collection and annotation are time-consuming, resource-intensive processes that often require domain expertise. Existing data collections such as animal sound collections provide valuable data sources, but their utilization is often hindered by the lack of fine-grained labels. In this study, we examine the use of existing weakly supervised methods
to extract fine-grained information from existing weakly-annotated data accumulated over time and alleviate the need for collection and annotation of fresh data. We employ TALNet, a Convolutional Recurrent Neural Network (CRNN) model and train it on 60-second sound recordings labeled for the presence of 42 different anuran species and compare it to other models such as BirdNet, a model for detection of bird vocalisation. We conduct the evaluation on 1-second segments, enabling precise sound event localization.
Furthermore, we investigate the impact of varying the length of the training input and explore different pooling functions' effects on the model's performance on AnuraSet. Finally, we integrate it in an interactive user interface that facilitates training and annotation. Our findings demonstrate the effectiveness of TALNet and BirdNet in harnessing weakly annotated sound collections for wildlife monitoring. Our method not only improves the extraction of information from coarse labels but also simplifies the process of annotating new data for experts.