{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/cbinfer-change-based-inference-for","title":"CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data","arxiv_id":"1704.04313","date":"2017-04-14","proceeding":null,"authors":["Lukas Cavigelli","Philippe Degen","Luca Benini"],"abstract":"Extracting per-frame features using convolutional neural networks for\nreal-time processing of video data is currently mainly performed on powerful\nGPU-accelerated workstations and compute clusters. However, there are many\napplications such as smart surveillance cameras that require or would benefit\nfrom on-site processing. To this end, we propose and evaluate a novel algorithm\nfor change-based evaluation of CNNs for video data recorded with a static\ncamera setting, exploiting the spatio-temporal sparsity of pixel changes. We\nachieve an average speed-up of 8.6x over a cuDNN baseline on a realistic\nbenchmark with a negligible accuracy loss of less than 0.1% and no retraining\nof the network. The resulting energy efficiency is 10x higher than that of\nper-frame evaluation and reaches an equivalent of 328 GOp/s/W on the Tegra X1\nplatform.","url_abs":"http://arxiv.org/abs/1704.04313v2","url_pdf":"http://arxiv.org/pdf/1704.04313v2.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":"cbinfer-change-based-inference-for","repo_url":"https://github.com/lukasc-ch/CBinfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.04313","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}