Mars-Bench: mb-mmls

This is a binary segmentation dataset designed to identify landslides on the Martian surface, with a focus on the Valles Marineris region from the CTX sensor. All annotations were manually created by expert geologists, ensuring high-quality, scientifically accurate labels. Each image sample includes multi-modal satellite data comprising 7 channels: RGB (3), Digital Elevation Model (DEM), thermal inertia, slope, and grayscale intensity. This rich set of modalities captures the complex geomorphology of landslide-prone regions, making the dataset especially valuable for developing and benchmarking robust segmentation models in planetary science. To explore all Mars-Bench resources, visit our project website: https://mars-bench.github.io/