{"url":"/dataset/epillid","name":"ePillID","full_name":null,"description_markdown":"**ePillID** is a benchmark for developing and evaluating computer vision models for pill identification. The ePillID benchmark is designed as a low-shot fine-grained benchmark, reflecting real-world challenges for developing image-based pill identification systems.\nThe characteristics of the ePillID benchmark include:\n* Reference and consumer images: The reference images are taken with controlled lighting and backgrounds, and with professional equipment. The consumer images are taken with real-world settings including different lighting, backgrounds, and equipment. For most of the pills, one image per side (two images per pill type) is available from the NIH Pillbox dataset.\n* Low-shot and fine-grained setting: 13k images representing 9804 appearance classes (two sides for 4902 pill types). For most of the appearance classes, there exists only one reference image, making it a challenging low-shot recognition setting.\n\nSource: [https://github.com/usuyama/ePillID-benchmark](https://github.com/usuyama/ePillID-benchmark)\nImage Source: [https://github.com/usuyama/ePillID-benchmark](https://github.com/usuyama/ePillID-benchmark)","description_withheld":null,"homepage":"https://github.com/usuyama/ePillID-benchmark","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/epillid-dataset-a-low-shot-fine-grained","title":"ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification","first_author":"Naoto Usuyama","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Pill Classification (Both Sides)","url":"/task/pill-classification-both-sides","datasets_with_task":"/datasets/task/pill-classification-both-sides"}],"languages":[],"variants":["ePillID"],"data_loaders":[{"repo":"https://github.com/usuyama/ePillID-benchmark","url":"https://github.com/usuyama/ePillID-benchmark","frameworks":["pytorch"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}