Abstract
This paper introduces SeaTurtleID, the first public large-scale, long-span dataset with sea turtle photographs captured in the wild. The dataset is suitable for benchmarking re-identification methods and evaluating several other computer vision tasks. The dataset consists of 7774 high-resolution photographs of 400 unique individuals collected within 12 years in 1081 encounters. Each photograph is accompanied by rich metadata, e.g., identity label, head segmentation mask, and encounter timestamp. The 12-year span of the dataset makes it the longest-spanned public wild animal dataset with timestamps. By exploiting this unique property, we show that timestamps are necessary for an unbiased evaluation of animal re-identification methods because they allow time-aware splits of the dataset into reference and query sets. We show that time-unaware splits can lead to performance overestimation of more than 100% compared to the time-aware splits for both feature- and CNN-based re-identification methods. We also argue that time-aware splits correspond to more realistic re-identification pipelines than the time-unaware ones. We recommend that animal re-identification methods should only be tested on datasets with timestamps using time-aware splits, and we encourage dataset curators to include such information in the associated metadata.
Abstract (translated)
URL
https://arxiv.org/abs/2211.10307
