Feathers dataset for Fine-Grained Visual Categorization
It provides a new dataset for fine-grained visual categorization in ornithology, but the method is incremental.
The paper introduces FeatherV1, a dataset of 28,272 feather images across 595 bird species for taxonomic identification, and reports classification results using DenseNet-based architectures with categorical cross-entropy comparisons.
This paper introduces a novel dataset FeatherV1, containing 28,272 images of feathers categorized by 595 bird species. It was created to perform taxonomic identification of bird species by a single feather, which can be applied in amateur and professional ornithology. FeatherV1 is the first publicly available bird's plumage dataset for machine learning, and it can raise interest for a new task in fine-grained visual recognition domain. The latest version of the dataset can be downloaded at https://github.com/feathers-dataset/feathersv1-dataset. We also present feathers classification task results. We selected several deep learning architectures (DenseNet based) for categorical crossentropy values comparison on the provided dataset.