'Continually Adapt or Not' or CAN Benchmark
A curated ICICLE benchmark for evaluating the performance of pre-trained models and fostering the development of adaptation algorithms in the camera trap domain.
References
Lila bc: Labeled information library of alexandria: Biology and conservation. https://lila.science/. 1, 3
Acknowledgements
National Science Foundation (NSF) funded AI institute for Intelligent Cyberinfrastructure with Computational Learning in the Environment (ICICLE) (OAC 2112606)
Issue reporting
To report any issue(s) with this benchmark, please create an issue in this github or contact: jeon.193@osu.edu