Best Practices to Train Deep Models on Imbalanced Datasets - A Case Study on Animal Detection in Aerial Imagery

摘要

We introduce recommendations to train a Convolutional Neural Network for grid-based detection on a dataset that has a substantial class imbalance. These include curriculum learning, hard negative mining, a special border class, and more. We evaluate the recommendations on the problem of animal detection in aerial images, where we obtain an increase in precision from 9% to 40% at high recalls, compared to state-of-the-art. Data related to this paper are available at: http:// doi.org/10.5281/zenodo.609023.