# ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification

arXiv: https://arxiv.org/abs/2005.14288 · HTML: https://mlsanity.com/paper/2005.14288/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2020.

## Built on by (most cited first, 3 of 3)

- [VeriMedi: Pill Identification using Proxy-based Deep Metric Learning and Exact Solution](https://mlsanity.com/paper/2104.11231/) (2021)
- [High Accurate and Explainable Multi-Pill Detection Framework with Graph Neural Network-Assisted Multimodal Data Fusion](https://mlsanity.com/paper/2303.09782/) (2023)
- [Evaluating Few-Shot Pill Recognition Under Visual Domain Shift](https://mlsanity.com/paper/2603.10833/) (2026)

## Abstract (arXiv)

Identifying prescription medications is a frequent task for patients and medical professionals; however, this is an error-prone task as many pills have similar appearances (e.g. white round pills), which increases the risk of medication errors. In this paper, we introduce ePillID, the largest public benchmark on pill image recognition, composed of 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. We present our experimental setup and evaluation results of various baseline models on the benchmark. The best baseline using a multi-head metric-learning approach with bilinear features performed remarkably well; however, our error analysis suggests that they still fail to distinguish particularly confusing classes. The code and data are available at https://github.com/usuyama/ePillID-benchmark.