{"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/visual-wake-words-dataset","title":"Visual Wake Words Dataset","arxiv_id":"1906.05721","date":"2019-06-12","proceeding":null,"authors":["Aakanksha Chowdhery","Pete Warden","Jonathon Shlens","Andrew Howard","Rocky Rhodes"],"abstract":"The emergence of Internet of Things (IoT) applications requires intelligence on the edge. Microcontrollers provide a low-cost compute platform to deploy intelligent IoT applications using machine learning at scale, but have extremely limited on-chip memory and compute capability. To deploy computer vision on such devices, we need tiny vision models that fit within a few hundred kilobytes of memory footprint in terms of peak usage and model size on device storage. To facilitate the development of microcontroller friendly models, we present a new dataset, Visual Wake Words, that represents a common microcontroller vision use-case of identifying whether a person is present in the image or not, and provides a realistic benchmark for tiny vision models. Within a limited memory footprint of 250 KB, several state-of-the-art mobile models achieve accuracy of 85-90% on the Visual Wake Words dataset. We anticipate the proposed dataset will advance the research on tiny vision models that can push the pareto-optimal boundary in terms of accuracy versus memory usage for microcontroller applications.","url_abs":"https://arxiv.org/abs/1906.05721v1","url_pdf":"https://arxiv.org/pdf/1906.05721v1.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":"visual-wake-words-dataset","repo_url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"visual-wake-words-dataset","repo_url":"https://github.com/Mxbonn/visualwakewords","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visual-wake-words-dataset","repo_url":"https://github.com/andreamattiagaravagno/colabnas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"visual-wake-words-dataset","repo_url":"https://github.com/arpit6232/visualwakeup_aesd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"visual-wake-words-dataset","repo_url":"https://github.com/dtch1997/tf-detect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"visual-wake-words","name":"Visual Wake Words","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.05721","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}