{"success":true,"data":{"author":"University of Twente (ITC); TACO repackaging by ISP, Universitat de Valencia","bucketAccessType":"public","bucketName":"isp-uv-es/ai4smallfarms-taco","bucketPrefix":"","category":"Agriculture & Environment","cloudProvider":"huggingface","createdAt":"2026-11-16T14:11:25.768Z","description":"AI4SmallFarms (IEEE GRSL, 2023) is a benchmark for delineating agricultural field boundaries in smallholder landscapes from 10 m Sentinel-2 imagery, where fields are often smaller than a hectare. It provides 62 tiles of about 5x5 km over Vietnam and Cambodia carrying 439,001 manually digitised field polygons, which form the benchmark, and 87 tiles over the Netherlands that the authors used for pretraining. Each sample is a native-size Sentinel-2 tile with bands B2, B3, B4 and B8 (reflectance x 10,000) and a binary field-extent mask; the release's own per-region splits are kept (103 train, 22 validation, 24 test tiles). About 550 MB in TACO format, read with tacoreader. The original is deposited in the DANS Data Station for Physical and Technical Sciences under CC BY 4.0; cite the AI4SmallFarms GRSL 2023 paper.","displayTitle":"AI4SmallFarms: Smallholder Crop Field Boundary Delineation from Sentinel-2, Vietnam and Cambodia (TACO)","doi":"10.1109/LGRS.2023.3323095","id":"1a9700cf-6419-5855-aeee-d49b03a86fda","license":"CC-BY-4.0","licenseEvidenceUrl":"https://phys-techsciences.datastations.nl/dataset.xhtml?persistentId=doi:10.17026/dans-xy6-ngg6","objectCountEstimate":9,"probeStatus":"ok","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"isp-uv-es/ai4smallfarms-taco\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"isp-uv-es/ai4smallfarms-taco\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=isp-uv-es, license:cc-by-4.0, size_categories:n<1K, format:imagefolder, downloads=129"],"format":"mixed","generatedAt":"2026-11-16T14:11:33.057Z","layout":{"example":"ai4smallfarms.zip","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"504b03040a0000080000d786385d3c6c4f18800000008000000009000c005f5f636f7a69705f5f0cca0800dd0c5f3f2c5a2782435a4950010002030000000f0019001700434f4c4c454354494f4e2e6a736f6e4d455441444154412f6368696c6472656e2e706172717565744d455441444154412f73616d706c652e70617271756574928edc20000000008fa2dc2000000000e9cddc2000000000c613000000000000252b000000000000a329000000000000504b03040a0000080000d686385d0da27efec5112f00c5112f0010000000444154412f302f696d6167652e74696649492a00d00000004744414c5f5354525543545552414c5f4d455441444154415f53495a453d3030303135362062797465730a4c41594f55543d494644535f4245464f52455f444154410a424c4f434b5f4f524445523d524f575f4d414a4f520a424c4f434b5f4c45414445523d53495a455f41535f55494e54340a424c4f434b5f545241494c45523d4c4153545f345f42595445535f52455045415445440a494e5445524c454156453d42414e440a4b4e4f574e5f494e434f4d50415449424c455f45444954494f4e3d4e4f0a200013000001030001000000ee0200000101030001000000fc0200000201030004000000ba010000030103000100000050c300000601030001000000010000001501030001000000040000001c01030001","encoding":"hex","key":"ai4smallfarms.zip","truncatedAt":512}],"sampleObjects":["ai4smallfarms.zip","assets/logos.png","assets/sample_0.png","assets/sample_1.png","assets/sample_2.png"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\npretty_name: \"AI4SmallFarms\"\nsize_categories:\n- n<1K\ntask_categories:\n- image-segmentation\ntags:\n- earth-observation\n- remote-sensing\n- taco\n---\n\n<p align=\"center\"><img src=\"assets/logos.png\" width=\"546\" alt=\"Image and Signal Processing Group, Universitat de València · ELLIOT\"></p>\n\n# AI4SmallFarms\n\n> **This is a repackaging, not a new dataset.** It is **AI4SmallFarms** by University of Twente ITC (Persello et al.), converted to TACO. Pixel values and labels are kept as released except where the description below says otherwise. All credit belongs to the original authors: if you use it, please cite them and follow their licence.\n>\n> [original dataset](https://phys-techsciences.datastations.nl/dataset.xhtml?persistentId=doi:10.17026/dans-xy6-ngg6) · [paper](https://doi.org/10.1109/LGRS.2023.3323095) · licence: CC-BY-4.0\n>\n> Repackaged into TACO by the [Image and Signal Processing Group (ISP)](https://isp.uv.es/), Universitat de València, within the [ELLIOT](https://elliot-ai.eu) project.\n\n## Citation\n\nPlease cite the original work:\n\n```bibtex\n@article{persello2023ai4smallfarms,\n  title   = {AI4SmallFarms: A Dataset for Crop Field Delineation in Southeast Asian Smallholder Farms},\n  author  = {Persello, Claudio and Grift, Jeroen and Fan, Xinyan and Paris, Claudia and H{\\\"a}nsch, Ronny and Koeva, Mila and Nelson, Andy},\n  journal = {IEEE Geoscience and Remote Sensing Letters},\n  volume  = {20}, pages = {1--5}, year = {2023},\n  doi     = {10.1109/LGRS.2023.3323095}\n}\n```\n\n## About the data\n\nCrop-field boundary delineation in smallholder landscapes: 149 Sentinel-2 tiles of about 5x5 km at 10 m (B2/B3/B4/B8, reflectance x 1e4) with a binary field mask.\n\n**149 samples** · splits: `test` 24 · `train` 103 · `validation` 22 · tasks: `semantic-segmentation`\n\nPackaged as [TACO v3](https://asterisk.coop/taco/spec/).\n\n<details>\n<summary>Full description</summary>\n\n- 62 tiles over Vietnam and Cambodia carrying 439,001 field polygons: the benchmark.\n- 87 tiles over the Netherlands, the authors' pre-training set.\n\n**Splits.** The release's own, per region.\n\n**Tiles.** Stored at their native size, not cropped.\n\n</details>\n\n## Getting started\n\n```bash\ngit clone --recursive https://github.com/OscarPellicer/taco\npip install -e \"taco/python[ml]\"     # builds the reader: C++23, CMake, Ninja, pkg-config, libcurl >= 7.83, OpenSSL >= 3\n```\n\nRead it straight from the Hub:\n\n```python\nimport os\nfrom huggingface_hub import hf_hub_download, snapshot_download\nfrom taco.ml import Dataset, plot_sample\n\npath = hf_hub_download(\"isp-uv-es/ai4smallfarms-taco\", \"ai4smallfarms.zip\", repo_type=\"dataset\")\nds = Dataset(path)\nplot_sample(ds[0])\n```\n\nor from a local copy:\n\n```python\nds = Dataset(\"ai4smallfarms.zip\")\nsample = ds[0]                      # {slot name: SlotValue}, arrays decoded\nsample[\"image\"].array.shape\n```\n\nMetadata without decoding anything:\n\n```python\nimport taco\ntaco.read(\"ai4smallfarms.zip\")              # one Arrow table, levels joined\n```\n\n## Samples\n\n![sample](assets/sample_0.png)\n![sample](assets/sample_1.png)\n![sample](assets/sample_2.png)\n![sample](assets/sample_3.png)\n![sample](assets/sample_4.png)\n\n## What a sample contains\n\n| role | slot | holds | modality | detail |\n|---|---|---|---|---|\n| input | `image` | raster | optical | 4 band(s), unit 1, scaled |\n| target | `field` | mask | label_raster | 2 classes |\n\n## Licence\n\nCC-BY-4.0\n\nProviders: University of Twente ITC (Persello et al.)\n\n## Acknowledgements\n\nTACO was designed by **César Aybar** and is specified at [https://asterisk.coop/taco/spec/](https://asterisk.coop/taco/spec/).\n\nBuilt by [Oscar Pellicer](https://scholar.google.com/citations?hl=es&user=CCFJshwAAAAJ&view_op=list_works&sortby=pubdate) within the [ELLIOT](https://elliot-ai.eu) project at the\n[Image and Signal Processing Group (ISP)](https://isp.uv.es/), Universitat de València.\n","encoding":"utf8","key":"README.md","name":"README.md","size":3884,"truncated":false}],"sourceObjectKey":"ai4smallfarms.zip","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"isp-uv-es/ai4smallfarms-taco\", filename=\"ai4smallfarms.zip\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"assets/logos.png","totalObjects":9},"summary":"AI4SmallFarms (IEEE GRSL, 2023) is a benchmark for delineating agricultural field boundaries in smallholder landscapes from 10 m Sentinel-2 imagery, where fields are often smaller…","title":"AI4SmallFarms: Smallholder Crop Field Boundary Delineation from Sentinel-2, Vietnam and Cambodia (TACO)","updatedAt":"2026-11-16T17:24:05.323Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/isp-uv-es/ai4smallfarms-taco"}}