{"success":true,"data":{"author":"Mirali Purohit, Hannah Kerner et al. (Mars-Bench, Arizona State University)","bucketAccessType":"public","bucketName":"Mirali33/mb-change_cls_hirise","bucketPrefix":"","category":"Astronomy & Space","cloudProvider":"huggingface","createdAt":"2026-11-18T00:06:03.577Z","description":"Binary change detection on the Martian surface from MRO HiRISE: 100 x 100 pixel composites stack a before image (blue channel) and an after image (green channel) of the same location, after Kerner et al. (2019), and are labeled change or no_change. Mars-Bench created train, validation and test splits (3,103 / 670 / 670 in the paper) because the source had none, and adds 1- to 20-shot training subsets. Use it alongside mb-change_cls_ctx to compare change detection at HiRISE (sub-meter) and CTX (meter-scale) resolution. Parquet shards under data/ with image and integer label, annotation.csv and mapping.json; load with datasets.load_dataset. About 30 MB. Part of Mars-Bench (Purohit et al., NeurIPS 2025 Datasets and Benchmarks track, arXiv:2510.24010), 20 standardized Mars datasets released by the authors under CC BY 4.0; cite Mars-Bench and Kerner et al. (2019).","displayTitle":"Mars-Bench Surface Change Detection, MRO HiRISE Before/After Composites","doi":"10.48550/arXiv.2510.24010","huggingFaceUrl":"https://huggingface.co/datasets/Mirali33/mb-change_cls_hirise","id":"8d9951da-0aa0-5109-af56-15e861b68313","license":"CC-BY-4.0","licenseEvidenceUrl":"https://arxiv.org/html/2510.24010v1","objectCountEstimate":20,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/Mirali33/mb-change_cls_hirise","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Mirali33/mb-change_cls_hirise\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Mirali33/mb-change_cls_hirise\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Mirali33, license:cc-by-4.0, size_categories:10K<n<100K, format:parquet, downloads=85"],"format":"mixed","generatedAt":"2026-11-18T00:09:00.175Z","layout":{"example":"annotation.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"file_id,split,feature_name,label\n26520_before.jpg,train,no_change,0\n20662_before.jpg,train,no_change,0\n24658_before.jpg,train,no_change,0\n25168_before.jpg,train,no_change,0\n24946_before.jpg,train,no_change,0\n23628_before.jpg,train,no_change,0\n26305_before.jpg,train,no_change,0\n22436_before.jpg,train,no_change,0\n25709_before.jpg,train,no_change,0\n23918_before.jpg,train,no_change,0\n20457_before.jpg,train,no_change,0\n22637_before.jpg,train,no_change,0\n27238_before.jpg,train,no_change,0\n27372_before.jpg,train,n","encoding":"utf8","key":"annotation.csv","truncatedAt":512}],"sampleObjects":["annotation.csv","data/few_shot_train_10_shot-00000-of-00001.parquet","data/few_shot_train_15_shot-00000-of-00001.parquet","data/few_shot_train_1_shot-00000-of-00001.parquet","data/few_shot_train_20_shot-00000-of-00001.parquet"],"sidecars":[{"bytes":"---\nannotations_creators:\n- expert-generated\nlanguage_creators:\n- found\nlanguage:\n- en\nlicense:\n- cc-by-4.0\nmultilinguality:\n- monolingual\nsize_categories:\n- 10K<n<100K\nsource_datasets:\n- original\ntask_categories:\n- image-classification\ntask_ids:\n- multi-class-image-classification\npretty_name: mb-change_cls_hirise\ndataset_info:\n  features:\n  - name: image\n    dtype: image\n  - name: label\n    dtype:\n      class_label:\n        names:\n          '0': no_change\n          '1': change\n---\n\n# mb-change_cls_hirise\n\nA Mars image classification dataset for planetary science research.\n\n## Dataset Metadata\n\n* **License:** CC-BY-4.0 (Creative Commons Attribution 4.0 International)\n* **Version:** 1.0\n* **Date Published:** 2025-05-22\n* **Cite As:** TBD\n\n## Classes\n\nThis dataset contains the following classes:\n\n- 0: no_change\n- 1: change\n\n## Statistics\n\n- **train**: 6206 images\n- **test**: 1340 images\n- **val**: 1340 images\n- **few_shot_train_2_shot**: 4 images\n- **few_shot_train_1_shot**: 2 images\n- **few_shot_train_10_shot**: 20 images\n- **few_shot_train_5_shot**: 10 images\n- **few_shot_train_15_shot**: 30 images\n- **few_shot_train_20_shot**: 40 images\n- **partition_train_0.01x_partition**: 31 images\n- **partition_train_0.02x_partition**: 62 images\n- **partition_train_0.50x_partition**: 1565 images\n- **partition_train_0.20x_partition**: 626 images\n- **partition_train_0.05x_partition**: 156 images\n- **partition_train_0.10x_partition**: 313 images\n- **partition_train_0.25x_partition**: 782 images\n\n## Few-shot Splits\n\nThis dataset includes the following few-shot training splits:\n\n- **few_shot_train_2_shot**: 4 images\n- **few_shot_train_1_shot**: 2 images\n- **few_shot_train_10_shot**: 20 images\n- **few_shot_train_5_shot**: 10 images\n- **few_shot_train_15_shot**: 30 images\n- **few_shot_train_20_shot**: 40 images\n\nFew-shot configurations:\n\n- **2_shot.csv**\n- **1_shot.csv**\n- **10_shot.csv**\n- **5_shot.csv**\n- **15_shot.csv**\n- **20_shot.csv**\n## Partition Splits\n\nThis dataset includes the following training data partitions:\n\n- **partition_train_0.01x_partition**: 31 images\n- **partition_train_0.02x_partition**: 62 images\n- **partition_train_0.50x_partition**: 1565 images\n- **partition_train_0.20x_partition**: 626 images\n- **partition_train_0.05x_partition**: 156 images\n- **partition_train_0.10x_partition**: 313 images\n- **partition_train_0.25x_partition**: 782 images\n\n## Usage\n\n```python\nfrom datasets import load_dataset\n\ndataset = load_dataset(\"Mirali33/mb-change_cls_hirise\")\n```\n\n## Format\n\nEach example in the dataset has the following format:\n\n```\n{\n  'image': Image(...),  # PIL image\n  'label': int,         # Class label\n}\n```\n","encoding":"utf8","key":"README.md","name":"README.md","size":2658,"truncated":false}],"sourceObjectKey":"annotation.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/Mirali33/mb-change_cls_hirise/annotation.csv\")\ndf.head()","starterSamplePath":"annotation.csv","totalObjects":20},"summary":"Binary change detection on the Martian surface from MRO HiRISE: 100 x 100 pixel composites stack a before image (blue channel) and an after image (green channel) of the same…","title":"Mars-Bench Surface Change Detection, MRO HiRISE Before/After Composites","updatedAt":"2026-11-18T04:03:47.546Z","visibility":"public","websiteUrl":"https://mars-bench.github.io/"}}