{"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/selective-deep-convolutional-features-for","title":"Selective Deep Convolutional Features for Image Retrieval","arxiv_id":"1707.00809","date":"2017-07-04","proceeding":null,"authors":["Tuan Hoang","Thanh-Toan Do","Dang-Khoa Le Tan","Ngai-Man Cheung"],"abstract":"Convolutional Neural Network (CNN) is a very powerful approach to extract\ndiscriminative local descriptors for effective image search. Recent work adopts\nfine-tuned strategies to further improve the discriminative power of the\ndescriptors. Taking a different approach, in this paper, we propose a novel\nframework to achieve competitive retrieval performance. Firstly, we propose\nvarious masking schemes, namely SIFT-mask, SUM-mask, and MAX-mask, to select a\nrepresentative subset of local convolutional features and remove a large number\nof redundant features. We demonstrate that this can effectively address the\nburstiness issue and improve retrieval accuracy. Secondly, we propose to employ\nrecent embedding and aggregating methods to further enhance feature\ndiscriminability. Extensive experiments demonstrate that our proposed framework\nachieves state-of-the-art retrieval accuracy.","url_abs":"http://arxiv.org/abs/1707.00809v2","url_pdf":"http://arxiv.org/pdf/1707.00809v2.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":"selective-deep-convolutional-features-for","repo_url":"https://github.com/hnanhtuan/selectiveConvFeature","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.00809","atlas_url":"https://app.syntology.ai/?focus=1707.00809","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":"1707.00809"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.00809\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.00809"},"call":"get_concepts_for_paper(arxiv_id=\"1707.00809\")"}],"by_repo":[{"repo":"hnanhtuan/selectiveConvFeature","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":"28e5fce7cbb9fb6349b9eda0d9717f9d6b1ae39125a53412440b23c953818074","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}