Abstract Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try overcome this problem by processing video or stereo sequences, which may not always be available. Instead, in paper, we propose domain adaptation approach train monocular estimation model using fully-annotated source dataset and non-annotated ...

Model generalization to the unseen scenes is crucial real-world applications, such as autonomous driving, which requires robust vision systems. To enhance model generalization, domain through learning domain-invariant representation has been widely studied. However, most existing works learn shared feature space within multi-source domains but ignore characteristic of itself (e.g., sensitivity ...

In this work, we introduce a new concept, named source-free open compound domain adaptation (SF-OCDA), and study it in semantic segmentation. SF-OCDA is more challenging than the traditional but practical. It jointly considers (1) issues of data privacy storage (2) scenario multiple target domains unseen domains. SF-OCDA, only source pre-trained model are available to learn model. The evaluated...

The segmentation of unlabeled medical images is troublesome due to the high cost annotation, and unsupervised domain adaptation one solution this. In this paper, an improved method was proposed. proposed considered both global alignment category-wise alignment. First, we aligned appearance two domains by image transformation. Second, output maps in a way. Then, decomposed semantic prediction ma...