Cross-domain object detection using unsupervised image translation

作者：

Highlights：

• A simple yet effective method for detecting objects on unsupervised domain adaptation.

• Artificially generated images are useful for unsupervised domain adaptation.

• An extensive comparison with the state-of-the-art is provided.

• Experiments in three scenarios: synthetic data, adverse weather, and cross-camera.

摘要

•A simple yet effective method for detecting objects on unsupervised domain adaptation.•Artificially generated images are useful for unsupervised domain adaptation.•An extensive comparison with the state-of-the-art is provided.•Experiments in three scenarios: synthetic data, adverse weather, and cross-camera.

论文关键词：Unsupervised Domain Adaptation,Object detection,Generative Adversarial Networks,Unpaired image-to-image translation,Style-transfer

论文评审过程：Received 1 June 2021, Revised 27 August 2021, Accepted 26 November 2021, Available online 11 December 2021, Version of Record 30 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116334