{"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/stacked-what-where-auto-encoders","title":"Stacked What-Where Auto-encoders","arxiv_id":"1506.02351","date":"2015-06-08","proceeding":null,"authors":["Junbo Zhao","Michael Mathieu","Ross Goroshin","Yann Lecun"],"abstract":"We present a novel architecture, the \"stacked what-where auto-encoders\"\n(SWWAE), which integrates discriminative and generative pathways and provides a\nunified approach to supervised, semi-supervised and unsupervised learning\nwithout relying on sampling during training. An instantiation of SWWAE uses a\nconvolutional net (Convnet) (LeCun et al. (1998)) to encode the input, and\nemploys a deconvolutional net (Deconvnet) (Zeiler et al. (2010)) to produce the\nreconstruction. The objective function includes reconstruction terms that\ninduce the hidden states in the Deconvnet to be similar to those of the\nConvnet. Each pooling layer produces two sets of variables: the \"what\" which\nare fed to the next layer, and its complementary variable \"where\" that are fed\nto the corresponding layer in the generative decoder.","url_abs":"http://arxiv.org/abs/1506.02351v8","url_pdf":"http://arxiv.org/pdf/1506.02351v8.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":"stacked-what-where-auto-encoders","repo_url":"https://github.com/isaacgerg/keras_odds_and_ends","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"stacked-what-where-auto-encoders","repo_url":"https://github.com/zhangqinghao0811/unpool","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":"image-classification","task_name":"Image Classification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"SWWAE","rank_in_archive_order":183,"of":265,"metrics":{"Percentage correct":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"SWWAE","rank_in_archive_order":178,"of":211,"metrics":{"Percentage correct":"69.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"Zhao et al. (2015) (auto-encoder)","rank_in_archive_order":62,"of":81,"metrics":{"Percentage error":"4.76"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"SWWAE","rank_in_archive_order":79,"of":117,"metrics":{"Percentage correct":"74.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-stl-1","task":"Semi-Supervised Image Classification","dataset":"STL-10, 1000 Labels","model":"SWWAE","rank_in_archive_order":13,"of":13,"metrics":{"Accuracy":"74.30"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02351","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}