Abstract
AbstractLarge amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only asking for respective labels, active learning can increase the efficiency of the labeling process in terms of time and cost. In this work, we describe combinations of an incremental learning scheme and methods of active learning. These allow for continuous exploration of newly observed unlabeled data. We describe selection criteria based on model uncertainty as well as expected model output change (EMOC). An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset. We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application where images from camera traps are analyzed. Labeling only 32 images by accepting or rejecting proposals generated by our method yields an increase in accuracy from 25.4 to 42.6%.
Publisher
Springer Science and Business Media LLC
Reference71 articles.
1. Abramson Y, Freund Y (2006) Active learning for visual object detection. Tech. rep., University of California, San Diego
2. Bietti A (2012) Active learning for object detection on satellite images. Tech. rep., California Institute of Technology, Pasadena
3. Brust CA, Burghardt T, Groenenberg M, Kading C, Kuhl HS, Manguette ML, Denzler J (2017) Towards automated visual monitoring of individual gorillas in the wild. In: The IEEE international conference on computer vision (ICCV) workshops
4. Brust CA, Käding C, Denzler J (2019) Active learning for deep object detection. In: International joint conference on computer vision, imaging and computer graphics theory and applications (VISAPP), pp 181–190. https://doi.org/10.5220/0007248601810190
5. Brust CA, Sickert S, Simon M, Rodner E, Denzler J (2015) Convolutional patch networks with spatial prior for road detection and urban scene understanding. In: International conference on computer vision theory and applications (VISAPP)
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献