Recognizing New Classes with Synthetic Data in the Loop : Application to Traffic Sign Recognition
Villalonga, Gabriel (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Weijer, Joost van de (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Data:	2020
Resum:	On-board vision systems may need to increase the number of classes that can be recognized in a relatively short period. For instance, a traffic sign recognition system may suddenly be required to recognize new signs. Since collecting and annotating samples of such new classes may need more time than we wish, especially for uncommon signs, we propose a method to generate these samples by combining synthetic images and Generative Adversarial Network (GAN) technology. In particular, the GAN is trained on synthetic and real-world samples from known classes to perform synthetic-to-real domain adaptation, but applied to synthetic samples of the new classes. Using the Tsinghua dataset with a synthetic counterpart, SYNTHIA-TS, we have run an extensive set of experiments. The results show that the proposed method is indeed effective, provided that we use a proper Convolutional Neural Network (CNN) to perform the traffic sign recognition (classification) task as well as a proper GAN to transform the synthetic images. Here, a ResNet101-based classifier and domain adaptation based on CycleGAN performed extremely well for a ratio for new/known classes; even for more challenging ratios such as , the results are also very positive.
Ajuts:	Agencia Estatal de Investigación TIN2017-88709-R Agencia Estatal de Investigación TIN2016-79717-R
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Matèria:	CNNs ; Training with synthetic data ; Traffic sign recognition
Publicat a:	Sensors (Basel, Switzerland), Vol. 20, Num. 3 (February 2020) , art. 583, ISSN 1424-8220

DOI: 10.3390/s20030583
PMID: 31973078

21 p, 9.4 MB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats