Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery Using Deep CNNs and Active Learning

Benjamin Kellenberger, Diego Marcos, Sylvain Lobry, Devis Tuia*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

18 Citations (Scopus)


We present an Active Learning (AL) strategy for reusing a deep Convolutional Neural Network (CNN)-based object detector on a new data set. This is of particular interest for wildlife conservation: given a set of images acquired with an Unmanned Aerial Vehicle (UAV) and manually labeled ground truth, our goal is to train an animal detector that can be reused for repeated acquisitions, e.g., in follow-up years. Domain shifts between data sets typically prevent such a direct model application. We thus propose to bridge this gap using AL and introduce a new criterion called Transfer Sampling (TS). TS uses Optimal Transport (OT) to find corresponding regions between the source and the target data sets in the space of CNN activations. The CNN scores in the source data set are used to rank the samples according to their likelihood of being animals, and this ranking is transferred to the target data set. Unlike conventional AL criteria that exploit model uncertainty, TS focuses on very confident samples, thus allowing quick retrieval of true positives in the target data set, where positives are typically extremely rare and difficult to find by visual inspection. We extend TS with a new window cropping strategy that further accelerates sample retrieval. Our experiments show that with both strategies combined, less than half a percent of oracle-provided labels are enough to find almost 80% of the animals in challenging sets of UAV images, beating all baselines by a margin.
Original languageEnglish
Pages (from-to)9524-9533
JournalIEEE Transactions on Geoscience and Remote Sensing
Issue number12
Publication statusPublished - Dec 2019

Fingerprint Dive into the research topics of 'Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery Using Deep CNNs and Active Learning'. Together they form a unique fingerprint.

Cite this