{"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/rethinking-spatial-invariance-of-1","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","arxiv_id":"2206.05253","date":"2022-06-10","proceeding":"CVPR 2022 1","authors":["Zhi-Qi Cheng","Qi Dai","Hong Li","Jingkuan Song","Xiao Wu","Alexander G. Hauptmann"],"abstract":"Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level spatial invariance would cause overfit noise in the density map generation. In this paper, we try to use locally connected Gaussian kernels to replace the original convolution filter to estimate the spatial position in the density map. The purpose of this is to allow the feature extraction process to potentially stimulate the density map generation process to overcome the annotation noise. Inspired by previous work, we propose a low-rank approximation accompanied with translation invariance to favorably implement the approximation of massive Gaussian convolution. Our work points a new direction for follow-up research, which should investigate how to properly relax the overly strict pixel-level spatial invariance for object counting. We evaluate our methods on 4 mainstream object counting networks (i.e., MCNN, CSRNet, SANet, and ResNet-50). Extensive experiments were conducted on 7 popular benchmarks for 3 applications (i.e., crowd, vehicle, and plant counting). Experimental results show that our methods significantly outperform other state-of-the-art methods and achieve promising learning of the spatial position of objects.","url_abs":"https://arxiv.org/abs/2206.05253v2","url_pdf":"https://arxiv.org/pdf/2206.05253v2.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":"rethinking-spatial-invariance-of-1","repo_url":"https://github.com/zhiqic/rethinking-counting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":null,"task_name":"Position"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/crowd-counting-on-jhu-crowd","task":"Crowd Counting","dataset":"JHU-CROWD++","model":"GauNet (ResNet-50)","rank_in_archive_order":2,"of":3,"metrics":{"MAE":"58.2","MSE":"245.1"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-shanghaitech-a","task":"Crowd Counting","dataset":"ShanghaiTech A","model":"GauNet (ResNet-50)","rank_in_archive_order":9,"of":35,"metrics":{"MAE":"54.8","MSE":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-shanghaitech-b","task":"Crowd Counting","dataset":"ShanghaiTech B","model":"GauNet (ResNet-50)","rank_in_archive_order":5,"of":32,"metrics":{"MAE":"6.0"},"uses_additional_data":true},{"leaderboard":"/sota/crowd-counting-on-ucf-cc-50","task":"Crowd Counting","dataset":"UCF CC 50","model":"GauNet (ResNet-50)","rank_in_archive_order":3,"of":22,"metrics":{"MAE":"186.3"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-ucf-qnrf","task":"Crowd Counting","dataset":"UCF-QNRF","model":"GauNet (ResNet-50)","rank_in_archive_order":9,"of":23,"metrics":{"MAE":"81.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-counting-on-trancos","task":"Object Counting","dataset":"TRANCOS","model":"GauNet (ResNet-50)","rank_in_archive_order":1,"of":1,"metrics":{"MAE":"2.1","MSE":"2.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.05253","atlas_url":"https://app.syntology.ai/?focus=2206.05253","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":"2206.05253"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2206.05253\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2206.05253"},"call":"get_concepts_for_paper(arxiv_id=\"2206.05253\")"}],"by_repo":[{"repo":"zhiqic/rethinking-counting","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":"6831d5318b8a79812ac98cd4a1ac749d08d5ba3dcc7272f79b01448defa7e9fa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}