Translator Disclaimer
31 January 2020 Unsupervised domain adaptation for DNN-based automated harvesting
Author Affiliations +
Proceedings Volume 11433, Twelfth International Conference on Machine Vision (ICMV 2019); 114330X (2020)
Event: Twelfth International Conference on Machine Vision, 2019, Amsterdam, Netherlands
Computer vision systems based on convolutional neural networks are being rapidly introduced in the field of precision agriculture to solve the problem of scene recognition. Convolutional networks allow performing high-precision recognition, but a significant problem is the expensive process of adapting the network to new conditions. This article proposes a method of fast adaptation of the trained network to minor changes in the source domain without annotating new data. This method is known as Adversarial Domain Adaptation, in the current paper it is applied to the problem of agricultural scene recognition in automated harvesting. The initial training procedure is modified for parallel training of an additional subnet on unannotated data, which makes it possible to compensate the domain shift due to adversarial training. This approach allows us to monotonically increase the quality of all recognized classes of objects and to enhance the stability of CNN model.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Aleksandr Yu. Shkanaev, Dmitry L. Sholomov, and Dmitry P. Nikolaev "Unsupervised domain adaptation for DNN-based automated harvesting", Proc. SPIE 11433, Twelfth International Conference on Machine Vision (ICMV 2019), 114330X (31 January 2020);

Back to Top