{"url":"/task/instance-search","name":"Instance Search","slug":"instance-search","description_markdown":"Visual **Instance Search** is the task of retrieving from a database of images the ones that contain an instance of a visual query. It is typically much more challenging than finding images from the database that contain objects belonging to the same category as the object in the query. If the visual query is an image of a shoe, visual Instance Search does not try to find images of shoes, which might differ from the query in shape, color or size, but tries to find images of the exact same shoe as the one in the query image. Visual Instance Search challenges image representations as the features extracted from the images must enable such fine-grained recognition despite variations in viewpoints, scale, position, illumination, etc. Whereas holistic image representations, where each image is mapped to a single high-dimensional vector, are sufficient for coarse-grained similarity retrieval, local features are needed for instance retrieval.\n\n\n<span class=\"description-source\">Source: [Dynamicity and Durability in Scalable Visual Instance Search ](https://arxiv.org/abs/1805.10942)</span>","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":9,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/oxford105k","name":"Oxford105k","full_name":"","num_papers_in_archive":44}],"subtasks":[{"url":"/task/audio-fingerprint","name":"Audio Fingerprint"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":9,"of":9,"tagged_in_all":29,"items":[{"url":"/paper/faster-r-cnn-features-for-instance-search","title":"Faster R-CNN Features for Instance Search","date":"2016-04-29","arxiv_id":"1604.08893","repositories_listed":3,"syntology":null},{"url":"/paper/class-weighted-convolutional-features-for","title":"Class-Weighted Convolutional Features for Visual Instance Search","date":"2017-07-09","arxiv_id":"1707.02581","repositories_listed":2,"syntology":null},{"url":"/paper/bags-of-local-convolutional-features-for","title":"Bags of Local Convolutional Features for Scalable Instance Search","date":"2016-04-15","arxiv_id":"1604.04653","repositories_listed":2,"syntology":null},{"url":"/paper/the-effect-of-points-dispersion-on-the-k-nn-1","title":"The Effect of Points Dispersion on the $k$-nn Search in Random Projection Forests","date":"2023-02-25","arxiv_id":"2302.13160","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-end-to-end-information","title":"Data-efficient End-to-end Information Extraction for Statistical Legal Analysis","date":"2022-11-03","arxiv_id":"2211.01692","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-aware-active-feedback-for","title":"Confidence-Aware Active Feedback for Interactive Instance Search","date":"2021-10-23","arxiv_id":"2110.12255","repositories_listed":1,"syntology":null},{"url":"/paper/trecvid-2020-a-comprehensive-campaign-for","title":"TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains","date":"2021-04-27","arxiv_id":"2104.13473","repositories_listed":1,"syntology":null},{"url":"/paper/globaltrack-a-simple-and-strong-baseline-for","title":"GlobalTrack: A Simple and Strong Baseline for Long-term Tracking","date":"2019-12-18","arxiv_id":"1912.08531","repositories_listed":1,"syntology":null},{"url":"/paper/saliency-weighted-convolutional-features-for","title":"Saliency Weighted Convolutional Features for Instance Search","date":"2017-11-29","arxiv_id":"1711.10795","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}