A minimal data set of mars32k

We conducted experiments to evaluate saliency mode performance on a portion of the mars32k dataset (available at https://dominikschmidt.xyz/mars32k/). This dataset is an unlabeled public dataset that contains 32,000 color images collected by the Curiosity rover on Mars between August 2012 and November 2018. The images show various geographical and geological features of Mars such as mountains and valleys, craters, dunes and rocky terrain.

本研究开展实验以评估显著性模式在火星32K数据集（mars32k，可从https://dominikschmidt.xyz/mars32k/获取）的子集上的性能。该数据集为无标注公开数据集，包含32000张由好奇号火星车（Curiosity rover）于2012年8月至2018年11月间在火星采集的彩色图像。这些图像展现了火星多样的地理与地质特征，涵盖山脉与山谷、撞击坑、沙丘及岩石地貌。