… the scientific literature related to our proposed domain adaptation approach. In Sect. 3 we
describe our approach to conditioning thermal domain adaptation on the auxiliary task of day/…

… imagery without requiring RGB-to-thermal image pairs. We propose an unsupervised domain
adaptation … and thermal image modalities. Numerous recent methods attempted to address …

… To the best of our knowledge, there is no active domain adaptation study in the literature
of thermal image classification. While the SDM [46] employs no extra classifiers for query by …

… several domain adaptation approaches to adapt RGB-trained detectors to the thermal domain.
… In Section 3, we describe several approaches to domain adaptation that we apply to the …

… thermal and visible spectrum imagery in … domain adaptation techniques for fine-tuning a
YOLOv3 detector to perform accurate and robust pedestrian detection using thermal images…

… thermal images is introduced in this study by domain adap… domain adaptation for other
datasets, like introducing foggy weather in the Kitti dataset or convert day images to night images…

… RGB-to-thermal domain adaptation method using a multi-domain attention network and
adversarial attention learning. • We evaluate our method on thermal image classification tasks …

… and thermal images which current record holders 16 exploit by using both spectral domains
in parallel for person detection. In contrast, this work will only use the thermal images from …

… This study focuses on thermal object detection since thermal imagery is a fundamental tool
… a robust thermal image object detector. The efficacy of a self-supervised thermal network is …

… domain to perform detection in the thermal domain at no additional annotation cost. Precisely,
we propose a domain adaptation … size of one visible image and one thermal image. Also, …