The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop
This dataset addresses the problem of evaluating semi-supervised learning methods in computer vision for fine-grained bird recognition, but it is incremental as it builds on existing datasets.
The authors introduced a new dataset for semi-supervised recognition of 1000 bird species with nearly 150k images, featuring challenges like out-of-domain data, class imbalance, and fine-grained similarity to test existing techniques.
This document describes the details and the motivation behind a new dataset we collected for the semi-supervised recognition challenge~\cite{semi-aves} at the FGVC7 workshop at CVPR 2020. The dataset contains 1000 species of birds sampled from the iNat-2018 dataset for a total of nearly 150k images. From this collection, we sample a subset of classes and their labels, while adding the images from the remaining classes to the unlabeled set of images. The presence of out-of-domain data (novel classes), high class-imbalance, and fine-grained similarity between classes poses significant challenges for existing semi-supervised recognition techniques in the literature. The dataset is available here: \url{https://github.com/cvl-umass/semi-inat-2020}