.png){kind=icon}
.png){kind=icon}
Return
Self-Supervised Domain Adaptation for Computer Vision Tasks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2949697.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 this link. (1)(1) https://github.com/Jiaolong/self-supervised-da
Keywords:
Task analysis
Semantics
Training
Image segmentation
Visualization
Data models
Object recognition
Domain adaptation
semantic segmentation
object recognition
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W