{"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/fast-feature-extraction-with-cnns-with","title":"Fast Feature Extraction with CNNs with Pooling Layers","arxiv_id":"1805.03096","date":"2018-05-08","proceeding":null,"authors":["Christian Bailer","Tewodros Habtegebrial","Kiran varanasi","Didier Stricker"],"abstract":"In recent years, many publications showed that convolutional neural network\nbased features can have a superior performance to engineered features. However,\nnot much effort was taken so far to extract local features efficiently for a\nwhole image. In this paper, we present an approach to compute patch-based local\nfeature descriptors efficiently in presence of pooling and striding layers for\nwhole images at once. Our approach is generic and can be applied to nearly all\nexisting network architectures. This includes networks for all local feature\nextraction tasks like camera calibration, Patchmatching, optical flow\nestimation and stereo matching. In addition, our approach can be applied to\nother patch-based approaches like sliding window object detection and\nrecognition. We complete our paper with a speed benchmark of popular CNN based\nfeature extraction approaches applied on a whole image, with and without our\nspeedup, and example code (for Torch) that shows how an arbitrary CNN\narchitecture can be easily converted by our approach.","url_abs":"http://arxiv.org/abs/1805.03096v1","url_pdf":"http://arxiv.org/pdf/1805.03096v1.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":"fast-feature-extraction-with-cnns-with","repo_url":"https://github.com/erezposner/Fast_Dense_Feature_Extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"camera-calibration","task_name":"Camera Calibration"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.03096","atlas_url":"https://app.syntology.ai/?focus=1805.03096","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":"1805.03096"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.03096\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.03096"},"call":"get_concepts_for_paper(arxiv_id=\"1805.03096\")"}],"by_repo":[{"repo":"erezposner/Fast_Dense_Feature_Extraction","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":"75eadd08d0433a7874aa222769c29ea49d5866b168061d3eec044013b9a8fc6e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}