{"success":true,"data":{"author":"Hakai Institute","bucketAccessType":"public","bucketName":"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024","bucketPrefix":"","category":"Environmental Science","cloudProvider":"huggingface","createdAt":"2026-11-21T20:45:58.717Z","description":"A three-class semantic segmentation dataset of rocky intertidal habitat from high resolution drone (UAV) RGB imagery collected by the Hakai Institute. Every pixel is labeled mussel, gooseneck barnacle or background, by manual heads-up digitizing with manual verification. There are 909 image and label pairs as non-overlapping 1024 by 1024 pixel TIFF tiles, packed as WebDataset tar shards with train, validation and test splits (about 3.8 GB) and a metadata.json; load with the datasets library (keys image.tif and label.tif) or stream the shards. Suited to training and benchmarking models that map intertidal invertebrate cover, a companion to the single-class MusselSeg dataset. Released by the Hakai Institute under CC BY 4.0; cite the dataset, DOI 10.57967/hf/7792.","displayTitle":"MusselGooseneckSeg: Drone Imagery Segmentation of Mussels and Gooseneck Barnacles in the Rocky Intertidal (Hakai Institute)","doi":"10.57967/hf/7792","huggingFaceUrl":"https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024","id":"c6d0351d-10be-560d-bac7-eec3b6d8740e","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024","objectCountEstimate":19,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=HakaiInstitute, license:cc-by-4.0, size_categories:n<1K, format:webdataset, downloads=201"],"format":"mixed","generatedAt":"2026-11-21T20:48:46.829Z","layout":{"example":"test-000000.tar","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"2e2f2e2f40506178486561646572000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000030303030303030003030303030303000303030303030300030303030303030303033340030303030303030303030300030313032313200207800000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000757374617200303000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000","encoding":"hex","key":"test-000000.tar","truncatedAt":512}],"sampleObjects":["test-000000.tar","train-000000.tar","train-000001.tar","train-000002.tar","train-000003.tar"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- image-segmentation\nlanguage:\n- en\ntags:\n- image\n- geospatial\n- biology\n- aerial imagery\n- remote sensing\npretty_name: MusselGooseneckSeg\nsize_categories:\n- 1K<n<10K\n---\n\n# MusselGooseneckSeg: Semantic Segmentation for Rocky Intertidal Mussel and Gooseneck Barnacle Habitat\n\n## Dataset description\n\nMusselGooseneckSeg is a dataset for semantic segmentation of mussel and gooseneck barnacle habitat using high resolution drone imagery. It provides pixel-wise annotation for mussels and gooseneck barnacles in rocky intertidal zones.\n\n- **Source:** Imagery collected by the Hakai Institute\n\n## Task description\n\nThe dataset is designed for semantic segmentation of mussel and gooseneck barnacle habitat in aerial imagery. The task involves assigning each pixel in the image to one of three classes: \"mussel\", \"gooseneck barnacle\", or \"background\".\n\n## Usage\n\n### Download and iterate\n\nInstall the HuggingFace datasets library ([instructions](https://huggingface.co/docs/datasets/en/installation))\n\n```python\nfrom datasets import load_dataset\n\ntrain_dataset = load_dataset(\"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024\", split=\"train\")\nval_dataset = load_dataset(\"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024\", split=\"validation\")\ntest_dataset  = load_dataset(\"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024\", split=\"test\")\n\nfor sample in train_dataset:\n    x = sample[\"image.tif\"]\n    y = sample[\"label.tif\"]\n    # x and y are `PIL.Image` instances, ready to feed into a training loop, PyTorch dataloader, etc.\n\n    # ...\n```\n\n### Streaming from HuggingFace\n\nThis data is released as a WebDatasets, which makes it possible to use the data without downloading it in advance. \nFor instructions on how to do this, please see [WebDataset](https://huggingface.co/docs/hub/en/datasets-webdataset)\n\n## Data characteristics\n\n- **Image Format:** TIFF\n- **Tile Size:** 1024x1024 pixels\n- **Tile Overlap:** None\n- **Number of Tiles:** 909 image and label pairs\n\n## Annotation details\n- **Method:** Manual heads-up digitizing with manual verification\n- **Format:** Pixel-wise labels stored as separate mask images\n- **Labelling Convention:** Each pixel assigned a single class label\n\n## Class distribution\n\n| Class ID | Class Name           | Description             | Percentage |\n| :------- | :------------------- | :---------------------- | :--------: |\n| 0        | Background           | Unclassified areas      | 85.15%     |\n| 1        | Mussels              | Mussel bed              | 8.08%      |\n| 2        | Gooseneck Barnacles  | Gooseneck barnacle bed  | 6.78%      |\n\n## Split information\n\n| Split      | Data Percentage | Tiles Count |\n| :--------- | --------------: | ----------: |\n| Train      |             89% |         811 |\n| Validation |              6% |          55 |\n| Test       |              5% |          46 |\n\n## Preprocessing\n\n1. Tiles extracted from source imagery\n2. Pixel-wise annotations applied for mussels and gooseneck barnacles\n\n## Licensing information\n\nThis dataset is released under the Creative Commons Attribution 4.0 License (CC BY 4.0).\n\n## Ethical considerations\n\n- No identifiable individuals are present in imagery\n- Minimized impact on wildlife and sensitive habitats\n- Engaged with local First Nations in planning aerial surveys\n\n## Citation information\n\nIf you use this dataset in your research,  please cite:\n\n```\n@misc{denouden2024musselgoosenecseg,\n  author = {Denouden, Taylor and McInnes, William and Guyn, Alex},\n  title = {MusselGooseneckSeg: Semantic Segmentation for Rocky Intertidal Mussel and Gooseneck Barnacle Habitat},\n  month = February,\n  year = 2026,\n  doi = { 10.57967/hf/7792 },\n  publisher = {Hakai Institute {\\tt data@hakai.org}},\n  howpublished = {\\url{https://huggingface.co/datasets/HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024}}\n}\n```\n\n## Known limitations\n- Imagery only covers areas with known mussel and gooseneck barnacle habitat\n- No examples near urban or built-up environments\n- Labelling errors may be present in areas with shadows, where it is difficult to disting","encoding":"utf8","key":"README.md","name":"README.md","size":4111,"truncated":true},{"bytes":"{\n  \"created\": \"2026-02-11T11:01:54.936365\",\n  \"config\": {\n    \"maxsize\": 250000000.0,\n    \"maxcount\": 500,\n    \"image_format\": \"tif\",\n    \"label_format\": \"tif\",\n    \"compression\": \"gzip\",\n    \"shuffle\": false\n  },\n  \"statistics\": [\n    {\n      \"split\": \"train\",\n      \"total_samples\": 810,\n      \"total_shards\": 14,\n      \"failed_files\": []\n    },\n    {\n      \"split\": \"val\",\n      \"total_samples\": 54,\n      \"total_shards\": 1,\n      \"failed_files\": []\n    },\n    {\n      \"split\": \"test\",\n      \"total_samples\": 45,\n      \"total_shards\": 1,\n      \"failed_files\": []\n    }\n  ]\n}","encoding":"utf8","key":"metadata.json","name":"metadata.json","size":578,"truncated":false}],"sourceObjectKey":"test-000000.tar","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"HakaiInstitute/mussel-gooseneck-seg-rgb-1024-1024\", filename=\"test-000000.tar\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"test-000000.tar","totalObjects":19},"summary":"A three-class semantic segmentation dataset of rocky intertidal habitat from high resolution drone (UAV) RGB imagery collected by the Hakai Institute.","title":"MusselGooseneckSeg: Drone Imagery Segmentation of Mussels and Gooseneck Barnacles in the Rocky Intertidal (Hakai Institute)","updatedAt":"2026-11-21T21:59:43.745Z","visibility":"public","websiteUrl":"https://hakai.org"}}