{"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/scale-adaptive-neural-dense-features-learning","title":"Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation","arxiv_id":"1903.10427","date":"2019-03-25","proceeding":"CVPR 2019 6","authors":["Jaime Spencer","Richard Bowden","Simon Hadfield"],"abstract":"How do computers and intelligent agents view the world around them? Feature\nextraction and representation constitutes one the basic building blocks towards\nanswering this question. Traditionally, this has been done with carefully\nengineered hand-crafted techniques such as HOG, SIFT or ORB. However, there is\nno ``one size fits all'' approach that satisfies all requirements. In recent\nyears, the rising popularity of deep learning has resulted in a myriad of\nend-to-end solutions to many computer vision problems. These approaches, while\nsuccessful, tend to lack scalability and can't easily exploit information\nlearned by other systems. Instead, we propose SAND features, a dedicated deep\nlearning solution to feature extraction capable of providing hierarchical\ncontext information. This is achieved by employing sparse relative labels\nindicating relationships of similarity/dissimilarity between image locations.\nThe nature of these labels results in an almost infinite set of dissimilar\nexamples to choose from. We demonstrate how the selection of negative examples\nduring training can be used to modify the feature space and vary it's\nproperties. To demonstrate the generality of this approach, we apply the\nproposed features to a multitude of tasks, each requiring different properties.\nThis includes disparity estimation, semantic segmentation, self-localisation\nand SLAM. In all cases, we show how incorporating SAND features results in\nbetter or comparable results to the baseline, whilst requiring little to no\nadditional training. Code can be found at:\nhttps://github.com/jspenmar/SAND_features","url_abs":"http://arxiv.org/abs/1903.10427v1","url_pdf":"http://arxiv.org/pdf/1903.10427v1.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":"scale-adaptive-neural-dense-features-learning","repo_url":"https://github.com/jspenmar/SAND_features","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":"sand","task_name":"Sand"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10427","atlas_url":"https://app.syntology.ai/?focus=1903.10427","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":"1903.10427"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.10427\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.10427"},"call":"get_concepts_for_paper(arxiv_id=\"1903.10427\")"}],"by_repo":[{"repo":"jspenmar/SAND_features","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":"8a5b408a386cfaa5ba33a3f8c750335f00103cdc613c288fa36fb0d751ea93c4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}