Industrial products typically lack defects in smart manufacturing systems, which leads to an
extremely imbalanced task of recognizing surface defects. With this imbalanced sample …

In an effort to further advance semi-supervised generative and classification tasks, we
propose a simple yet effective training strategy called* dual pseudo training*(DPT), built …

Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised
models due to its effect in hurting the generalization performance of deep neural networks …

Three-dimensional point cloud data are widely used in many fields, as they can be easily
obtained and contain rich semantic information. Recently, weakly supervised segmentation …

With the emergence of AI generated content, cross-modal retrieval of 2D and 3D data has
obtained increasing research attention. In practical applications, massive amounts of 2D and …

Oriented object detectors have achieved great success in aerial detection tasks with the help
of ample labeled data. Unlabeled images are easier and less expensive to obtain than …

Dieses Buch ist eine Einführung in naturanaloge Techniken und verwandte formale
Methoden. Zu jeder Technik werden Anwendungsbeispiele gegeben. Dargestellt werden …

Polyp segmentation technology based on deep learning can quickly and accurately help
doctors locate lesions, but its development is limited by pixel-level annotations. The polyp …

Semi-supervised learning has made remarkable strides by effectively utilizing a limited
amount of labeled data while capitalizing on the abundant information present in unlabeled …

Aerial images present significant challenges to label-driven supervised learning, in
particular, the annotation of substantial small-sized objects is a highly laborious process. To …