Hiroshi Sasaki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hiroshi Sasaki has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chris G. Willcocks
Durham University
2 shared publications - Peter Hessey
Durham University
1 shared publication - Sam Bond-Taylor
Department of Computer Science Durham University
1 shared publication Toby P. Breckon
Durham University, Durham, UK
1 shared publication- Toby P. Breckon
Department of Computer Science, Durham University, Durham, UK
1 shared publication
Latest Publications
- 10 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5083-5090
Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to the limited quantity and variety of non-visible spectral domain imagery, in contrast to the high data availability of visible-band imagery that readily enables contemporary deep learning driven detection and classification approaches. To address this problem, this paper proposes and evaluates a novel data augmentation approach that leverages the more readily available visible-band imagery via a generative domain transfer model. The model can synthesise large volumes of non-visible domain imagery by image-to-image (I2I) translation from the visible image domain. Furthermore, we show that the generation of interpolated mixed class (non-visible domain) image examples via our novel Conditional CycleGAN Mixup Augmentation (C2GMA) methodology can lead to a significant improvement in the quality of non-visible domain classification tasks that otherwise suffer due to limited data availability. Focusing on classification within the Synthetic Aperture Radar (SAR) domain, our approach is evaluated on a variation of the Statoil/C-CORE Iceberg Classifier Challenge dataset and achieves 75.4 % accuracy, demonstrating a significant improvement when compared against traditional data augmentation strategies (Rotation, Mixup, and MixCycleGAN).
- 10 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5083-5090
Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to the limited quantity and variety of non-visible spectral domain imagery, in contrast to the high data availability of visible-band imagery that readily enables contemporary deep learning driven detection and classification approaches. To address this problem, this paper proposes and evaluates a novel data augmentation approach that leverages the more readily available visible-band imagery via a generative domain transfer model. The model can synthesise large volumes of non-visible domain imagery by image-to-image (I2I) translation from the visible image domain. Furthermore, we show that the generation of interpolated mixed class (non-visible domain) image examples via our novel Conditional CycleGAN Mixup Augmentation (C2GMA) methodology can lead to a significant improvement in the quality of non-visible domain classification tasks that otherwise suffer due to limited data availability. Focusing on classification within the Synthetic Aperture Radar (SAR) domain, our approach is evaluated on a variation of the Statoil/C-CORE Iceberg Classifier Challenge dataset and achieves 75.4 % accuracy, demonstrating a significant improvement when compared against traditional data augmentation strategies (Rotation, Mixup, and MixCycleGAN).