iBioHash2023

Overview


This competition requires participants to deal with the large-scale fine-grained image search task based on learning-to-hash techniques. The dataset contains 2,000 fine-grained categories. More concretely, 1,000 categories with 400,000 images are used for training, while the remaining 1,000 categories with 100,000 images are divided into the query set (having 10,000 images) and the gallery set (having 90,000 images) for evaluation.

Competition

Organizers