Self-Supervised Domain Adaptation for Computer Vision Tasks
| Autor: | Antonio M. López, Jiaolong Xu, Liang Xiao |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Normalization (statistics) Computer Science - Machine Learning General Computer Science Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences object recognition Machine Learning (cs.LG) 0202 electrical engineering electronic engineering information engineering Code (cryptography) General Materials Science Segmentation Computer vision Use case Layer (object-oriented design) Adaptation (computer science) 0105 earth and related environmental sciences Domain adaptation business.industry General Engineering Cognitive neuroscience of visual object recognition semantic segmentation 020201 artificial intelligence & image processing Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business Feature learning lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 7, Pp 156694-156706 (2019) |
| ISSN: | 2169-3536 |
| Popis: | Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work, we propose a generic method for self-supervised domain adaptation, using object recognition and semantic segmentation of urban scenes as use cases. Focusing on simple pretext/auxiliary tasks (e.g. image rotation prediction), we assess different learning strategies to improve domain adaptation effectiveness by self-supervision. Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy on semantic segmentation within our method, consisting of prediction layer alignment and batch normalization calibration. The experimental results show adaptation levels comparable to most studied domain adaptation methods, thus, bringing self-supervision as a new alternative for reaching domain adaptation. The code is available at https://github.com/Jiaolong/self-supervised-da. Comment: Accepted by IEEE Access |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|