Generative Data Augmentation for Vehicle Detection in Aerial Images

Kumdakcı H., Öngün C., TEMİZEL A.

25th International Conference on Pattern Recognition Workshops, ICPR 2020, Milan, İtalya, 10 - 11 Ocak 2021, cilt.12668 LNCS, ss.19-31 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 12668 LNCS
  • Doi Numarası: 10.1007/978-3-030-68793-9_2
  • Basıldığı Şehir: Milan
  • Basıldığı Ülke: İtalya
  • Sayfa Sayıları: ss.19-31
  • Anahtar Kelimeler: Data augmentation, Drone, UAV, Vehicle detection
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

© 2021, Springer Nature Switzerland AG.Scarcity of training data is one of the prominent problems for deep networks which require large amounts data. Data augmentation is a widely used method to increase the number of training samples and their variations. In this paper, we focus on improving vehicle detection performance in aerial images and propose a generative augmentation method which does not need any extra supervision than the bounding box annotations of the vehicle objects in the training dataset. The proposed method increases the performance of vehicle detection by allowing detectors to be trained with higher number of instances, especially when there are limited number of training instances. The proposed method is generic in the sense that it can be integrated with different generators. The experiments show that the method increases the Average Precision by up to 25.2% and 25.7% when integrated with Pluralistic and DeepFill respectively.