{"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/stochastic-downsampling-for-cost-adjustable","title":"Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks","arxiv_id":"1801.09335","date":"2018-01-29","proceeding":"CVPR 2018 6","authors":["Jason Kuen","Xiangfei Kong","Zhe Lin","Gang Wang","Jianxiong Yin","Simon See","Yap-Peng Tan"],"abstract":"It is desirable to train convolutional networks (CNNs) to run more\nefficiently during inference. In many cases however, the computational budget\nthat the system has for inference cannot be known beforehand during training,\nor the inference budget is dependent on the changing real-time resource\navailability. Thus, it is inadequate to train just inference-efficient CNNs,\nwhose inference costs are not adjustable and cannot adapt to varied inference\nbudgets. We propose a novel approach for cost-adjustable inference in CNNs -\nStochastic Downsampling Point (SDPoint). During training, SDPoint applies\nfeature map downsampling to a random point in the layer hierarchy, with a\nrandom downsampling ratio. The different stochastic downsampling configurations\nknown as SDPoint instances (of the same model) have computational costs\ndifferent from each other, while being trained to minimize the same prediction\nloss. Sharing network parameters across different instances provides\nsignificant regularization boost. During inference, one may handpick a SDPoint\ninstance that best fits the inference budget. The effectiveness of SDPoint, as\nboth a cost-adjustable inference approach and a regularizer, is validated\nthrough extensive experiments on image classification.","url_abs":"http://arxiv.org/abs/1801.09335v1","url_pdf":"http://arxiv.org/pdf/1801.09335v1.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":"stochastic-downsampling-for-cost-adjustable","repo_url":"https://github.com/xternalz/SDPoint","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.09335","atlas_url":"https://app.syntology.ai/?focus=1801.09335","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":"1801.09335"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.09335\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.09335"},"call":"get_concepts_for_paper(arxiv_id=\"1801.09335\")"}],"by_repo":[{"repo":"xternalz/SDPoint","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":"84e4736b5380923db4dc43fa8ad76e6d3c0a86b6f1ac3c225390bef0c94547ca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}