{"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/split-brain-autoencoders-unsupervised","title":"Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction","arxiv_id":"1611.09842","date":"2016-11-29","proceeding":"CVPR 2017 7","authors":["Richard Zhang","Phillip Isola","Alexei A. Efros"],"abstract":"We propose split-brain autoencoders, a straightforward modification of the\ntraditional autoencoder architecture, for unsupervised representation learning.\nThe method adds a split to the network, resulting in two disjoint sub-networks.\nEach sub-network is trained to perform a difficult task -- predicting one\nsubset of the data channels from another. Together, the sub-networks extract\nfeatures from the entire input signal. By forcing the network to solve\ncross-channel prediction tasks, we induce a representation within the network\nwhich transfers well to other, unseen tasks. This method achieves\nstate-of-the-art performance on several large-scale transfer learning\nbenchmarks.","url_abs":"http://arxiv.org/abs/1611.09842v3","url_pdf":"http://arxiv.org/pdf/1611.09842v3.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":"split-brain-autoencoders-unsupervised","repo_url":"https://github.com/richzhang/splitbrainauto","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"split-brain-autoencoders-unsupervised","repo_url":"https://github.com/ysharma1126/Split-Brain-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"Split-Brain (AlexNet)","rank_in_archive_order":141,"of":144,"metrics":{"Number of Params":"61M","Top 1 Accuracy":"35.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.09842","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}