{"url":"/dataset/ilias","name":"ILIAS","full_name":"ILIAS: Instance-Level Image retrieval At Scale","description_markdown":"**ILIAS** is a large-scale test dataset for evaluation on **Instance-Level Image retrieval At Scale**. It is designed to support future research in **image-to-image** and **text-to-image** retrieval for particular objects and serves as a benchmark for evaluating representations of foundation or customized vision and vision-language models, as well as specialized retrieval techniques. \r\n\r\n[**website**](https://vrg.fel.cvut.cz/ilias/)  |  [**dataset**](https://vrg.fel.cvut.cz/ilias_data/)  |  [**arxiv**](https://arxiv.org/abs/2502.11748) | [**huggingface**](https://huggingface.co/datasets/vrg-prague/ilias)\r\n\r\n## Composition\r\nThe dataset includes **1,000 object instances** across diverse domains, with:\r\n* **5,947 images** in total:\r\n  * **1,232 image queries**, depicting query objects on clean or uniform background\r\n  * **4,715 positive images**, featuring the query objects in real-world conditions with clutter, occlusions, scale variations, and partial views\r\n* **1,000 text queries**, providing fine-grained textual descriptions of the query objects\r\n* **100M distractors** from YFCC100M to evaluate retrieval performance under large-scale settings, while asserting noise-free ground truth","description_withheld":null,"homepage":"https://vrg.fel.cvut.cz/ilias/","introduced_date":"2025-02-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/ilias-instance-level-image-retrieval-at-scale","title":"ILIAS: Instance-Level Image retrieval At Scale","first_author":"Giorgos Kordopatis-Zilos","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/deed.en"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Zero-shot Text-to-Image Retrieval","url":"/task/zero-shot-text-to-image-retrieval","datasets_with_task":"/datasets/task/zero-shot-text-to-image-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ILIAS"],"data_loaders":[],"num_papers_in_archive":1,"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."}