{"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/denoising-autoencoder-with-modulated-lateral","title":"Denoising autoencoder with modulated lateral connections learns invariant representations of natural images","arxiv_id":"1412.7210","date":"2014-12-22","proceeding":null,"authors":["Antti Rasmus","Tapani Raiko","Harri Valpola"],"abstract":"Suitable lateral connections between encoder and decoder are shown to allow\nhigher layers of a denoising autoencoder (dAE) to focus on invariant\nrepresentations. In regular autoencoders, detailed information needs to be\ncarried through the highest layers but lateral connections from encoder to\ndecoder relieve this pressure. It is shown that abstract invariant features can\nbe translated to detailed reconstructions when invariant features are allowed\nto modulate the strength of the lateral connection. Three dAE structures with\nmodulated and additive lateral connections, and without lateral connections\nwere compared in experiments using real-world images. The experiments verify\nthat adding modulated lateral connections to the model 1) improves the accuracy\nof the probability model for inputs, as measured by denoising performance; 2)\nresults in representations whose degree of invariance grows faster towards the\nhigher layers; and 3) supports the formation of diverse invariant poolings.","url_abs":"http://arxiv.org/abs/1412.7210v4","url_pdf":"http://arxiv.org/pdf/1412.7210v4.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":"denoising-autoencoder-with-modulated-lateral","repo_url":"https://github.com/AbhinavS99/Ladder-Networks-for-Sign-Languages","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}