swissALPS: a Dataset for Imbalanced Land Cover Mapping in Alpine Regions

Our large scale alpine land cover dataset consists of  229'535 very high-resolution aerial images (50cm) and  digital elevation model (50cm) with land cover annotations  produced by  experts in photo-interpretration . The nine land cover types in our study area include bedrock, bedrock with grass, large blocks, large blocks with grass, scree, scree with grass, water area, forest and glacier. The distribution of pixels among classes presents a typical case of a long-tailed distribution with an imbalance factor, defined as the ratio of the most frequent to the rarest class, close to 1000. The data are taken from the Federal Office of Topography - swisstopo