Authors:
Robby Neven
and
Toon Goedemé
Affiliation:
PSI-EAVISE, KU Leuven, Jan Pieter De Nayerlaan, Sint-Katelijne-Waver, Belgium
Keyword(s):
Deep Learning, Machine Learning, Computer Vision, Active Learning.
Abstract:
Recently, deep learning approaches excel in important computer vision tasks like classification and segmentation. The downside, however, is that they are very data hungry, which is very costly. One way to address this issue is by using active learning: only label and train on diverse and informative data points, not wasting any effort on redundant data. While recent active learning approaches have difficulty combining diversity and informativeness, we propose a sampling technique which efficiently combines these two metrics into a single algorithm. This is achieved by adapting a Determinantal Point Process to also consider model uncertainty. We first show competitive results on the academic classification datasets CIFAR10 and CalTech101, and the CityScapes segmentation task. To further increase the performance of our sampler on segmentation tasks, we extend our method to a patch-based active learning approach, improving the performance by not wasting labelling effort on redundant ima
ge regions. Lastly, we demonstrate our method on a more challenging realworld industrial use-case, segmenting defects in steel sheet material, which greatly benefits from an active learning approach due to a vast amount of redundant data, and show promising results.
(More)