Cross-domain object detection using unsupervised image translation

Arruda, Vinicius F.; Berriel, Rodrigo F.; Paixão, Thiago M.; Badué, Claudine; Souza, Alberto F. De; Sebe, Nicu; Oliveira-Santos, Thiago

doi:10.1016/j.eswa.2021.116334

Cited by 11 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Car AP MAF-ICCV'2019 [53] 72.10 SWDA-CVPR'2019 [48] 71.00 ATF-ECCV'2020 [75] 73.50 ART-CVPR'2020 [29] 73.60 GPA-CVPR'2020 [52] 65.36 SGA-TMM'2021 [76] 72.02 UIT-ESwA'2022 [77] 73.70 ParaUDA-TITS'2022 [70] 72.20 IDF-TCSVT'2023 [78] 74.00…”

Section: Methodologiesmentioning

confidence: 99%

Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather

et al. 2023

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, however such assumption may fail in different weather conditions. Due to the domain gap, a detection model trained under clear weather may not perform well in foggy and rainy conditions. Overcoming detection bottlenecks in foggy and rainy weather is a real challenge for autonomous vehicles deployed in the wild. To bridge the domain gap and improve the performance of object detectionin foggy and rainy weather, this paper presents a novel framework for domain-adaptive object detection. The adaptations at both the image-level and objectlevel are intended to minimize the differences in image style and object appearance between domains. Furthermore, in order to improve the model's performance on challenging examples, we introduce a novel adversarial gradient reversal layer that conducts adversarial mining on difficult instances in addition to domain adaptation. Additionally, we suggest generating an auxiliary domain through data augmentation to enforce a new domain-level metric regularization. Experimental findings on public V2V benchmark exhibit a substantial enhancement in object detection specifically for foggy and rainy driving scenarios.

show abstract