{"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/coda-counting-objects-via-scale-aware","title":"CODA: Counting Objects via Scale-aware Adversarial Density Adaption","arxiv_id":"1903.10442","date":"2019-03-25","proceeding":null,"authors":["Li Wang","Yongbo Li","xiangyang xue"],"abstract":"Recent advances in crowd counting have achieved promising results with\nincreasingly complex convolutional neural network designs. However, due to the\nunpredictable domain shift, generalizing trained model to unseen scenarios is\noften suboptimal. Inspired by the observation that density maps of different\nscenarios share similar local structures, we propose a novel adversarial\nlearning approach in this paper, i.e., CODA (\\emph{Counting Objects via\nscale-aware adversarial Density Adaption}). To deal with different object\nscales and density distributions, we perform adversarial training with pyramid\npatches of multi-scales from both source- and target-domain. Along with a\nranking constraint across levels of the pyramid input, consistent object counts\ncan be produced for different scales. Extensive experiments demonstrate that\nour network produces much better results on unseen datasets compared with\nexisting counting adaption models. Notably, the performance of our CODA is\ncomparable with the state-of-the-art fully-supervised models that are trained\non the target dataset. Further analysis indicates that our density adaption\nframework can effortlessly extend to scenarios with different objects.\n\\emph{The code is available at https://github.com/Willy0919/CODA.}","url_abs":"http://arxiv.org/abs/1903.10442v1","url_pdf":"http://arxiv.org/pdf/1903.10442v1.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":"coda-counting-objects-via-scale-aware","repo_url":"https://github.com/Willy0919/CODA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10442","atlas_url":"https://app.syntology.ai/?focus=1903.10442","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":"1903.10442"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.10442\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.10442"},"call":"get_concepts_for_paper(arxiv_id=\"1903.10442\")"}],"by_repo":[{"repo":"Willy0919/CODA","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":"8c3222faaca74cf2aa0110a419b55383c67cd6633a5b9b67ad230606a73be2af","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}