{"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/what-is-the-best-practice-for-cnns-applied-to","title":"What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?","arxiv_id":"1611.01640","date":"2016-11-05","proceeding":null,"authors":["Jiedong Hao","Jing Dong","Wei Wang","Tieniu Tan"],"abstract":"Previous work has shown that feature maps of deep convolutional neural\nnetworks (CNNs) can be interpreted as feature representation of a particular\nimage region. Features aggregated from these feature maps have been exploited\nfor image retrieval tasks and achieved state-of-the-art performances in recent\nyears. The key to the success of such methods is the feature representation.\nHowever, the different factors that impact the effectiveness of features are\nstill not explored thoroughly. There are much less discussion about the best\ncombination of them.\n  The main contribution of our paper is the thorough evaluations of the various\nfactors that affect the discriminative ability of the features extracted from\nCNNs. Based on the evaluation results, we also identify the best choices for\ndifferent factors and propose a new multi-scale image feature representation\nmethod to encode the image effectively. Finally, we show that the proposed\nmethod generalises well and outperforms the state-of-the-art methods on four\ntypical datasets used for visual instance retrieval.","url_abs":"http://arxiv.org/abs/1611.01640v1","url_pdf":"http://arxiv.org/pdf/1611.01640v1.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":"what-is-the-best-practice-for-cnns-applied-to","repo_url":"https://github.com/hbwang1427/image_retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"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/1611.01640","atlas_url":"https://app.syntology.ai/?focus=1611.01640","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":"1611.01640"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1611.01640\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1611.01640"},"call":"get_concepts_for_paper(arxiv_id=\"1611.01640\")"}],"by_repo":[{"repo":"hbwang1427/image_retrieval","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":"9b27b9c32a202095fc92f93d56b478562b9855af0649d9217434fecc9f7270cb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}