Texture Underfitting for Domain Adaptation
| Autor: | Jan-Nico Zaech, Martin Hahner, Dengxin Dai, Luc Van Gool |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Artificial neural network Computer science business.industry Process (engineering) Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Overfitting Machine learning computer.software_genre Convolutional neural network Image (mathematics) Task (project management) 020204 information systems 0202 electrical engineering electronic engineering information engineering Key (cryptography) 020201 artificial intelligence & image processing Segmentation Artificial intelligence business computer |
| Zdroj: | ITSC |
| DOI: | 10.1109/itsc.2019.8917059 |
| Popis: | Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this task. However, a segmentation algorithm generalizing to various scenes and conditions would require an enormously diverse dataset, making the labour intensive data acquisition and labeling process prohibitively expensive. Under the assumption of structural similarities between segmentation maps, domain adaptation promises to resolve this challenge by transferring knowledge from existing, potentially simulated datasets to new environments where no supervision exists. While the performance of this approach is contingent on the concept that neural networks learn a high level understanding of scene structure, recent work suggests that neural networks are biased towards overfitting to texture instead of learning structural and shape information. Considering the ideas underlying semantic segmentation, we employ random image stylization to augment the training dataset and propose a training procedure that facilitates texture underfitting to improve the performance of domain adaptation. In experiments with supervised as well as unsupervised methods for the task of synthetic-to-real domain adaptation, we show that our approach outperforms conventional training methods. Accepted manuscript, IEEE Intelligent Transportation Systems Conference, 6 pages |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|