Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Object detectors often suffer from the domain gap between training (source domain) and real-
world applications (target domain). Mean-teacher self-training is a powerful paradigm in …

Most object detection methods for autonomous driving usually assume a onsistent feature
distribution between training and testing data, which is not always the case when weathers …

Self-training approaches recently achieved promising results in cross-domain object
detection, where people iteratively generate pseudo labels for unlabeled target domain …

Abstract Domain adaptive object detection (DAOD) aims to alleviate transfer performance
degradation caused by the cross-domain discrepancy. However, most existing DAOD …

Abstract Domain adaptive Object Detection (DAOD) leverages a labeled domain (source) to
learn an object detector generalizing to a novel domain without annotation (target). Recent …

Unsupervised domain adaptive object detection (UDA-OD) aims to learn a detector by
generalizing knowledge from a labeled source domain to an unlabeled target domain …

Abstract Domain adaptive object detection aims to adapt detection models to domains
where annotated data is unavailable. Existing methods have been proposed to address the …

Convolutional neural networks (CNNs) have demonstrated gratifying results at learning
discriminative features. However, when applied to unseen domains, state-of-the-art models …

In self-driving cars, adverse weather (eg, fog, rain, snow, and cloud) or occlusion scenarios
result in domain shift being unavoidable in object detection. Researchers have recently …