{"url":"/task/content-based-image-retrieval","name":"Content-Based Image Retrieval","slug":"content-based-image-retrieval","description_markdown":"**Content-Based Image Retrieval** is a well studied problem in computer vision, with retrieval problems generally divided into two groups: category-level retrieval and instance-level retrieval. Given a query image of the Sydney Harbour bridge, for instance, category-level retrieval aims to find any bridge in a given dataset of images, whilst instance-level retrieval must find the Sydney Harbour bridge to be considered a match.\n\n\n<span class=\"description-source\">Source: [Camera Obscurer: Generative Art for Design Inspiration ](https://arxiv.org/abs/1903.02165)</span>","categories":[{"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":195,"papers_with_code":34,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":5,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/content-based-image-retrieval-on-inria-1","slug":"content-based-image-retrieval-on-inria-1","dataset":"INRIA Holidays Dataset","dataset_url":"/dataset/inria-holidays-dataset","rows_in_archive":1,"metrics":["MAP"],"first_row_in_archive_order":{"model":"LHRR","paper_title":"Multimedia Retrieval Through Unsupervised Hypergraph-Based Manifold Ranking","paper_url":"/paper/multimedia-retrieval-through-unsupervised","paper_date":"2019-12-01","arxiv_id":null,"code_links":[{"title":"UDLF/UDLF","url":"https://github.com/UDLF/UDLF"}],"syntology":null}}],"datasets":[{"url":"/dataset/oxford5k","name":"Oxford5k","full_name":"Oxford Buildings","num_papers_in_archive":137},{"url":"/dataset/ps-battles","name":"PS-Battles","full_name":"","num_papers_in_archive":7},{"url":"/dataset/gpr1200","name":"GPR1200","full_name":"","num_papers_in_archive":3},{"url":"/dataset/european-flood-2013-dataset","name":"European Flood 2013 Dataset","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/inria-holidays-dataset","name":"INRIA Holidays Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/drone-navigation","name":"Drone navigation"},{"url":"/task/drone-view-target-localization","name":"Drone-view target localization"}],"parent_tasks":[{"url":"/task/image-retrieval","name":"Image Retrieval"}],"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":30,"of":34,"tagged_in_all":195,"items":[{"url":"/paper/a-clinically-motivated-self-supervised","title":"A clinically motivated self-supervised approach for content-based image retrieval of CT liver images","date":"2022-07-11","arxiv_id":"2207.04812","repositories_listed":2,"syntology":null},{"url":"/paper/conditioned-and-composed-image-retrieval","title":"Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features","date":"2022-06-19","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/gpr1200-a-benchmark-for-general-purpose","title":"GPR1200: A Benchmark for General-Purpose Content-Based Image Retrieval","date":"2021-11-25","arxiv_id":"2111.13122","repositories_listed":2,"syntology":null},{"url":"/paper/making-classification-competitive-for-deep","title":"Classification is a Strong Baseline for Deep Metric Learning","date":"2018-11-30","arxiv_id":"1811.12649","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/dual-path-convolutional-image-text-embedding","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","date":"2017-11-15","arxiv_id":"1711.05535","repositories_listed":2,"syntology":null},{"url":"/paper/content-based-image-retrieval-tutorial","title":"Content-based image retrieval tutorial","date":"2016-08-12","arxiv_id":"1608.03811","repositories_listed":2,"syntology":null},{"url":"/paper/obd-finder-explainable-coarse-to-fine-text","title":"OBD-Finder: Explainable Coarse-to-Fine Text-Centric Oracle Bone Duplicates Discovery","date":"2025-05-04","arxiv_id":"2505.03836","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-via-classifier-impact-and","title":"Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval","date":"2024-12-03","arxiv_id":"2412.02310","repositories_listed":1,"syntology":null},{"url":"/paper/saliency-map-based-image-retrieval-using","title":"Saliency Map-based Image Retrieval using Invariant Krawtchouk Moments","date":"2024-11-13","arxiv_id":"2411.08567","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-foundation-models-for-content","title":"Leveraging Foundation Models for Content-Based Medical Image Retrieval in Radiology","date":"2024-03-11","arxiv_id":"2403.06567","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-masked-autoencoders-for-sensor","title":"Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing","date":"2024-01-15","arxiv_id":"2401.07782","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-visual-and-semantic-similarity","title":"Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval","date":"2023-08-16","arxiv_id":"2308.08431","repositories_listed":1,"syntology":null},{"url":"/paper/iqpp-a-benchmark-for-image-query-performance","title":"iQPP: A Benchmark for Image Query Performance Prediction","date":"2023-02-20","arxiv_id":"2302.10126","repositories_listed":1,"syntology":null},{"url":"/paper/norppa-novel-ringed-seal-re-identification-by","title":"NORPPA: NOvel Ringed seal re-identification by Pelage Pattern Aggregation","date":"2022-06-06","arxiv_id":"2206.02498","repositories_listed":1,"syntology":null},{"url":"/paper/adatriplet-adaptive-gradient-triplet-loss","title":"AdaTriplet: Adaptive Gradient Triplet Loss with Automatic Margin Learning for Forensic Medical Image Matching","date":"2022-05-05","arxiv_id":"2205.02849","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modality-sub-image-retrieval-using","title":"Cross-Modality Sub-Image Retrieval using Contrastive Multimodal Image Representations","date":"2022-01-10","arxiv_id":"2201.03597","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-similarity-aggregation-with-self","title":"Contextual Similarity Aggregation with Self-attention for Visual Re-ranking","date":"2021-10-26","arxiv_id":"2110.13430","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/iart-a-search-engine-for-art-historical","title":"iART: A Search Engine for Art-Historical Images to Support Research in the Humanities","date":"2021-08-03","arxiv_id":"2108.01542","repositories_listed":1,"syntology":null},{"url":"/paper/city-scale-visual-place-recognition-with-deep","title":"City-Scale Visual Place Recognition with Deep Local Features Based on Multi-Scale Ordered VLAD Pooling","date":"2020-09-19","arxiv_id":"2009.09255","repositories_listed":1,"syntology":null},{"url":"/paper/privacy-leakage-of-sift-features-via-deep","title":"Privacy Leakage of SIFT Features via Deep Generative Model based Image Reconstruction","date":"2020-09-02","arxiv_id":"2009.01030","repositories_listed":1,"syntology":null},{"url":"/paper/pyretri-a-pytorch-based-library-for","title":"PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks","date":"2020-05-02","arxiv_id":"2005.02154","repositories_listed":1,"syntology":null},{"url":"/paper/cbir-using-features-derived-by-deep-learning","title":"CBIR using features derived by Deep Learning","date":"2020-02-13","arxiv_id":"2002.07877","repositories_listed":1,"syntology":null},{"url":"/paper/multimedia-retrieval-through-unsupervised","title":"Multimedia Retrieval Through Unsupervised Hypergraph-Based Manifold Ranking","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-flood-impact-analysis-using","title":"Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images","date":"2019-08-09","arxiv_id":"1908.03361","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-hierarchy-preserving-deep-hashing","title":"Semantic Hierarchy Preserving Deep Hashing for Large-scale Image Retrieval","date":"2019-01-31","arxiv_id":"1901.11259","repositories_listed":1,"syntology":null},{"url":"/paper/whos-afraid-of-adversarial-queries-the-impact","title":"Who's Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrieval","date":"2019-01-29","arxiv_id":"1901.10332","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/information-theoretic-active-learning-for","title":"Information-Theoretic Active Learning for Content-Based Image Retrieval","date":"2018-09-07","arxiv_id":"1809.02337","repositories_listed":1,"syntology":null},{"url":"/paper/image-super-resolution-via-feature-augmented","title":"Image Super-resolution via Feature-augmented Random Forest","date":"2017-12-14","arxiv_id":"1712.05248","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-query-image-disambiguation-for","title":"Automatic Query Image Disambiguation for Content-Based Image Retrieval","date":"2017-11-02","arxiv_id":"1711.00953","repositories_listed":1,"syntology":null},{"url":"/paper/convex-formulation-of-multiple-instance","title":"Convex Formulation of Multiple Instance Learning from Positive and Unlabeled Bags","date":"2017-04-22","arxiv_id":"1704.06767","repositories_listed":1,"syntology":null}],"syntology_records":3,"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":"2026-09-25T09:33:49+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"}}