1. Improving Synthetic to Realistic Semantic Segmentation With Parallel Generative Ensembles for Autonomous Urban Driving
- Author
-
Hui Fang, Mohammed A. Quddus, Jungong Han, Yining Hua, Jinya Su, and Dewei Yi
- Subjects
Pixel ,business.industry ,Computer science ,Deep learning ,Reliability (computer networking) ,Image processing ,Machine learning ,computer.software_genre ,Domain (software engineering) ,Artificial Intelligence ,Robustness (computer science) ,Segmentation ,Artificial intelligence ,business ,Representation (mathematics) ,computer ,Software - Abstract
Semantic segmentation is paramount for autonomous vehicles to have a deeper understanding of the surrounding traffic environment and enhance safety. Deep neural networks (DNN) have achieved remarkable performances in semantic segmentation. However, training such a DNN requires a large amount of labelled data at pixel level. In practice, it is a labour-intensive task to manually annotate dense pixel-level labels. To tackle the problem associated with a small amount of labelled data, Deep Domain Adaptation (DDA) methods have recently been developed to examine the use of synthetic driving scenes so as to significantly reduce the manual annotation cost. Despite remarkable advances, these methods unfortunately suffer from the generalisability problem that fails to provide a holistic representation of the mapping from the source image domain to the target image domain. In this paper, we therefore develop a novel ensembled DDA to train models with different up-sampling strategies, discrepancy and segmentation loss functions. The models are, therefore, complementary with each other to achieve better generalisation in the target image domain. Such a design does not only improve the adapted semantic segmentation performance, but also strengthen the model reliability and robustness. Extensive experimental results demonstrate the superiorities of our approach over several state-of-the-art methods.
- Published
- 2022