{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/neural-codes-for-image-retrieval","title":"Neural Codes for Image Retrieval","arxiv_id":"1404.1777","date":"2014-04-07","proceeding":null,"authors":["Artem Babenko","Anton Slesarev","Alexandr Chigorin","Victor Lempitsky"],"abstract":"It has been shown that the activations invoked by an image within the top\nlayers of a large convolutional neural network provide a high-level descriptor\nof the visual content of the image. In this paper, we investigate the use of\nsuch descriptors (neural codes) within the image retrieval application. In the\nexperiments with several standard retrieval benchmarks, we establish that\nneural codes perform competitively even when the convolutional neural network\nhas been trained for an unrelated classification task (e.g.\\ Image-Net). We\nalso evaluate the improvement in the retrieval performance of neural codes,\nwhen the network is retrained on a dataset of images that are similar to images\nencountered at test time.\n  We further evaluate the performance of the compressed neural codes and show\nthat a simple PCA compression provides very good short codes that give\nstate-of-the-art accuracy on a number of datasets. In general, neural codes\nturn out to be much more resilient to such compression in comparison other\nstate-of-the-art descriptors. Finally, we show that discriminative\ndimensionality reduction trained on a dataset of pairs of matched photographs\nimproves the performance of PCA-compressed neural codes even further. Overall,\nour quantitative experiments demonstrate the promise of neural codes as visual\ndescriptors for image retrieval.","url_abs":"http://arxiv.org/abs/1404.1777v2","url_pdf":"http://arxiv.org/pdf/1404.1777v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-codes-for-image-retrieval","repo_url":"https://github.com/surajiyer/Recommender-Systems","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1404.1777","atlas_url":"https://app.syntology.ai/?focus=1404.1777","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1404.1777"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1404.1777\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1404.1777"},"call":"get_concepts_for_paper(arxiv_id=\"1404.1777\")"}],"by_repo":[{"repo":"surajiyer/Recommender-Systems","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2594191dc0bf04a69f10620f176f27a77d5c806e3da12c8851e85d24e3b9ed37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}