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

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.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  Ferda Ofli,et al.  Combining Human Computing and Machine Learning to Make Sense of Big (Aerial) Data for Disaster Response , 2016, Big Data.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Devis Tuia,et al.  Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning , 2018, Remote Sensing of Environment.

[5]  Michele Volpi,et al.  Detecting animals in African Savanna with UAVs and the crowds , 2017, ArXiv.

[6]  Julie Linchant,et al.  Are unmanned aircraft systems (UASs) the future of wildlife monitoring? A review of accomplishments and challenges , 2015 .

[7]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[10]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.