arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.02673cs.CV
收藏

基于注意力的增强行人对抗外观学习

Attention-based Adversarial Appearance Learning of Augmented Pedestrians

Technical University of Munich(慕尼黑工业大学);BMW(宝马公司);Google(谷歌公司)

Kevin Strauss, Artem Savkin, Federico Tombari

AI总结:

本文提出一种结合增强过程与对抗训练的方法,利用对抗损失驱动的注意力机制学习域差异并改善sim2real适应,从而为行人识别任务合成具有视觉真实性与语义一致性的逼真数据。

摘要:

合成数据已成为自动驾驶领域基于机器学习的感知的重要组成部分。然而由于sim2real域偏移,它仍无法完全替代真实数据。在本工作中,我们提出一种利用增强过程和对抗训练优势的方法,为行人识别任务合成逼真数据。我们的方法利用由对抗损失驱动的注意力机制来学习域差异并改善sim2real适应。实验证实,所提出的适应方法对此类差异具有鲁棒性,并展现出视觉真实性与语义一致性。此外,我们在行人识别任务上评估了数据生成pipeline,并证明生成的数据具有真实域的特性。

英文摘要:

Synthetic data became already an essential component of machine learning-based perception in the field of autonomous driving. Yet it still cannot replace real data completely due to the sim2real domain shift. In this work, we propose a method that leverages the advantages of the augmentation process and adversarial training to synthesize realistic data for the pedestrian recognition task. Our approach utilizes an attention mechanism driven by an adversarial loss to learn domain discrepancies and improve sim2real adaptation. Our experiments confirm that the proposed adaptation method is robust to such discrepancies and reveals both visual realism and semantic consistency. Furthermore, we evaluate our data generation pipeline on the task of pedestrian recognition and demonstrate that generated data resemble properties of the real domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑