.png){kind=icon}
.png){kind=icon}
Return
Cross-domain object detection using unsupervised image translation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2021.116334.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features proven to be promising, achieving state-of-the-art results. However, these methods are laborious to implement and hard to interpret. Although promising, there is still room for improvements to close the performance gap toward the upper-bound (when training with the target data). In this work, we propose a method to generate an artificial dataset in the target domain to train an object detector. We employed two unsupervised image translators (CycleGAN and an AdaIN-based model) using only annotated data from the source domain and non-annotated data from the target domain. Our key contributions are the proposal of a less complex yet more effective method that also has an improved interpretability. Results on real-world scenarios for autonomous driving show significant improvements, outperforming state-of-the-art methods in most cases, further closing the gap toward the upper-bound.
Keywords:
Unsupervised Domain Adaptation
Object detection
Generative Adversarial Networks
Unpaired image-to-image translation
Style-transfer
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W