Publication
Wild Data Treasures: Towards Sustainable Practices in Deep Learning for Wildlife Monitoring
Ilira Troshani; Thiago Gouvea; Daniel Sonntag
In: CHI EA '24: Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems. CHI Workshop on Sustaining Scalable Sustainability, Human-Centered Green Technology for Community-wide Carbon Reduction, located at ACM CHI 2024, May 11, Honolulu, HI, USA, ISBN 979-8-4007-0331-7, ACM, New York, USA, 5/2024.
Abstract
While data collection and annotation is crucial for training super- vised machine learning models and improving their accuracy, it can be resource-intensive. In this paper, we propose a weakly su- pervised method 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 also integrate it in an interactive tool that facilitates training and annotation. Communities comprising ecologists and other domain experts can use it to train machine learning models to detect animal species and monitor wildlife in protected areas. Our method not only improves the extraction of information from coarse labels but also simplifies the process of annotating new data for experts.. By lowering the time and expertise barrier to data annotation, we also aim to en- courage individuals with varying levels of expertise to participate more in citizen science and contribute to preserving ecosystems.