Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition

Wei He, Kai Han, Ying Nie, Chengcheng Wang, Yunhe Wang

Keywords: Invasion biometrics, Fine-grained dataset, Pre-training

Abstract: The development of foundation vision models has pushed the general visual recognition to a high level, but cannot well address the fine-grained recognition in specialized domain such as invasive species classification. Identifying and managing invasive species has strong social and ecological value. Currently, most invasive species datasets are limited in scale and cover a narrow range of species, which restricts the development of deep-learning based invasion biometrics systems. To fill the gap of this area, we introduced Species196, a large-scale semi-supervised dataset of 196-category invasive species. It collects over 19K images with expert-level accurate annotations (Species196-L), and 1.2M unlabeled images of invasive species (Species196-U). The dataset provides four experimental settings for benchmarking the existing models and algorithms, namely, supervised learning, semi-supervised learning and self-supervised pretraining. To facilitate future research on these four learning paradigms, we conduct an empirical study of the representative methods on the introduced dataset. The dataset will be made publicly available at https://species-dataset.github.io/.

Submission Number: 753