{"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/sparse-models-for-computer-vision","title":"Sparse models for Computer Vision","arxiv_id":"1701.06859","date":"2017-01-24","proceeding":null,"authors":["Laurent Perrinet"],"abstract":"The representation of images in the brain is known to be sparse. That is, as\nneural activity is recorded in a visual area ---for instance the primary visual\ncortex of primates--- only a few neurons are active at a given time with\nrespect to the whole population. It is believed that such a property reflects\nthe efficient match of the representation with the statistics of natural\nscenes. Applying such a paradigm to computer vision therefore seems a promising\napproach towards more biomimetic algorithms. Herein, we will describe a\nbiologically-inspired approach to this problem. First, we will describe an\nunsupervised learning paradigm which is particularly adapted to the efficient\ncoding of image patches. Then, we will outline a complete multi-scale framework\n---SparseLets--- implementing a biologically inspired sparse representation of\nnatural images. Finally, we will propose novel methods for integrating prior\ninformation into these algorithms and provide some preliminary experimental\nresults. We will conclude by giving some perspective on applying such\nalgorithms to computer vision. More specifically, we will propose that\nbio-inspired approaches may be applied to computer vision using predictive\ncoding schemes, sparse models being one simple and efficient instance of such\nschemes.","url_abs":"http://arxiv.org/abs/1701.06859v1","url_pdf":"http://arxiv.org/pdf/1701.06859v1.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":"sparse-models-for-computer-vision","repo_url":"https://github.com/bicv/Perrinet2015BICV_sparse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}