Sea Star Re-ID 2023
- Provider
- Oscar Wahltinez and Sharon Wahltinez
- License
- CDLA-Permissive-1.0 (source)
- Stored at
- Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/sea-star-re-id
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://lila.science/datasets/sea-star-re-id-2023
About Sea Star Re-ID 2023
Images for individual re-identification of sea stars: 1,204 images of 39 individual Asterias rubens (ASRU), photographed on five separate days, and 983 images of 56 individual Anthenea australiae (ANAU), photographed in sunlight, shade and a naturalistic exhibit on one day. Images are grouped into one folder per individual (folders beginning Asru or Anau), so the class structure suits torchvision ImageFolder style loaders for few-shot and metric learning. Layout (measured 2026-11-13): the folder holds a single archive, sea-star-re-id.zip (1.9 GB); nothing is unzipped, so on the read-only mount copy the zip to local disk and extract it before use. Use for few-shot re-identification of marine invertebrates, echinoderm photo-identification and individual-level population monitoring in aquaria and the field. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Wahltinez and Wahltinez, An Open-Source General Purpose Machine Learning Framework for Individual Animal Re-Identification Using Few-Shot Learning, Methods in Ecology and Evolution 2024.
How to access Sea Star Re-ID 2023 in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/sea-star-re-id/')[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
Files
Example file: sea-star-re-id.zip
Analyze this dataset without downloading it
On Scigantic, Sea Star Re-ID 2023 opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Environmental Science datasets
- Climate and Economic Justice Screening Tool (cloud-native formats)
- National Wetlands Inventory
- LakeATLAS v1.0 Lake Polygons and Pour Points with Hydro-environmental Attributes
- WABAD: World Annotated Bird Acoustic Dataset (3-second segments)
- United States Protected Areas Database (PAD-US) 3.0
- Wild Me Individual Animal Re-identification Sets (leopard, hyena, beluga, whale shark, zebra and giraffe)
- Nearshore Fish Atlas of Alaska: Pooled Beach Seine, Purse Seine and Trawl Catches, 1976-2022
- Barro Colorado Island 50-ha Plot Crown Maps, CanopyRS Preprocessed Tiles: Drone RGB Tree Crowns of a Panamanian Tropical Forest (Smithsonian)