{"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/iterative-manifold-embedding-layer-learned-by","title":"Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval","arxiv_id":"1707.09862","date":"2017-07-14","proceeding":null,"authors":["Jian Xu","Chunheng Wang","Chengzuo Qi","Cunzhao Shi","Baihua Xiao"],"abstract":"Existing manifold learning methods are not appropriate for image retrieval\ntask, because most of them are unable to process query image and they have much\nadditional computational cost especially for large scale database. Therefore,\nwe propose the iterative manifold embedding (IME) layer, of which the weights\nare learned off-line by unsupervised strategy, to explore the intrinsic\nmanifolds by incomplete data. On the large scale database that contains 27000\nimages, IME layer is more than 120 times faster than other manifold learning\nmethods to embed the original representations at query time. We embed the\noriginal descriptors of database images which lie on manifold in a high\ndimensional space into manifold-based representations iteratively to generate\nthe IME representations in off-line learning stage. According to the original\ndescriptors and the IME representations of database images, we estimate the\nweights of IME layer by ridge regression. In on-line retrieval stage, we employ\nthe IME layer to map the original representation of query image with ignorable\ntime cost (2 milliseconds). We experiment on five public standard datasets for\nimage retrieval. The proposed IME layer significantly outperforms related\ndimension reduction methods and manifold learning methods. Without\npost-processing, Our IME layer achieves a boost in performance of\nstate-of-the-art image retrieval methods with post-processing on most datasets,\nand needs less computational cost.","url_abs":"http://arxiv.org/abs/1707.09862v2","url_pdf":"http://arxiv.org/pdf/1707.09862v2.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":"iterative-manifold-embedding-layer-learned-by","repo_url":"https://github.com/XJhaoren/IME_layer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-instre","task":"Image Retrieval","dataset":"INSTRE","model":"IME layer","rank_in_archive_order":1,"of":1,"metrics":{"MAP":"82.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf105k","task":"Image Retrieval","dataset":"Oxf105k","model":"CNN+IME layer","rank_in_archive_order":4,"of":9,"metrics":{"MAP":"87.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf105k","task":"Image Retrieval","dataset":"Oxf105k","model":"SIFT+IME layer","rank_in_archive_order":9,"of":9,"metrics":{"MAP":"31.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf5k","task":"Image Retrieval","dataset":"Oxf5k","model":"CNN+IME layer","rank_in_archive_order":2,"of":11,"metrics":{"MAP":"92%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf5k","task":"Image Retrieval","dataset":"Oxf5k","model":"IME","rank_in_archive_order":6,"of":11,"metrics":{"MAP":"83.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf5k","task":"Image Retrieval","dataset":"Oxf5k","model":"PCA [51]","rank_in_archive_order":8,"of":11,"metrics":{"MAP":"82.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf5k","task":"Image Retrieval","dataset":"Oxf5k","model":"IsoMap [32]","rank_in_archive_order":9,"of":11,"metrics":{"MAP":"77.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf5k","task":"Image Retrieval","dataset":"Oxf5k","model":"SIFT+IME layer","rank_in_archive_order":10,"of":11,"metrics":{"MAP":"62.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-oxf5k","task":"Image Retrieval","dataset":"Oxf5k","model":"LLE [33]","rank_in_archive_order":11,"of":11,"metrics":{"MAP":"51.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-paris6k","task":"Image Retrieval","dataset":"Paris6k","model":"IME layer","rank_in_archive_order":1,"of":2,"metrics":{"mAP":"96.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"XJhaoren/IME_layer","kind":"official","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":"735b13373edb668eb25e271b96d0070e4b365767353b4ce2dbb5d2c7b5094691","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}