Artificial Intelligence

Acquiring imagery of extraterrestrial planetary surfaces has consistently posed a significant challenge. Moreover, the availability of publicly accessible, annotated lunar datasets remains exceedingly sparse. To address this gap in the field, we have developed the Real Chang'e Lunar Landscape Dataset. The images in this dataset were captured by the landing cameras of the Chang'e-3, Chang'e-4, and Chang'e-5 lunar mission probes, as well as the panoramic and terrain cameras carried by the Yutu-1 and Yutu-2 lunar rovers used during the missions.

In order to improve the efficiency and quality of salt-and-pepper denoising and realize the strategy of ‘denoising after judging’, the noise image classification network (CNN-J) is needed to judge whether the input image is a noisy image. For noisy images, the noise marking network (CNN-M) and noise denoising network (CNN-D) are combined for denoising processing, and the clean image will be directly output. In order to train the above three networks, three datasets are provided here, which are dataset_J, dataset_M and dataset_D, respectively.

eterogeneous graph representation learning is crit-

ical for analyzing complex data structures. Metapaths within this

field are vital as they elucidate high-order relationships across the

graph, significantly enhancing the model’s accuracy and depth of

understanding. However, metapaths tend to prioritize long-range

dependencies of the target node, which can lead to the oversight of

potentially crucial 1st-order heterogeneous neighbors or short-

range dependencies. To address this challenge and circumvent

The small rectal cancer dataset only consists of 190 MR images (including ADC, DCE, DWI and T2WI images), which can be categorized into 2 classes, i.e., T2 and T3. Fig. 2 illustrates some of the original MR images about T2 and T3 in the rectal cancer dataset. The ground-truth labels about tumor and rectum for all MR images are defined by one gastrointestinal radiologist.