{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/regularization-with-stochastic","title":"Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning","arxiv_id":"1606.04586","date":"2016-06-14","proceeding":"NeurIPS 2016 12","authors":["Mehdi Sajjadi","Mehran Javanmardi","Tolga Tasdizen"],"abstract":"Effective convolutional neural networks are trained on large sets of labeled\ndata. However, creating large labeled datasets is a very costly and\ntime-consuming task. Semi-supervised learning uses unlabeled data to train a\nmodel with higher accuracy when there is a limited set of labeled data\navailable. In this paper, we consider the problem of semi-supervised learning\nwith convolutional neural networks. Techniques such as randomized data\naugmentation, dropout and random max-pooling provide better generalization and\nstability for classifiers that are trained using gradient descent. Multiple\npasses of an individual sample through the network might lead to different\npredictions due to the non-deterministic behavior of these techniques. We\npropose an unsupervised loss function that takes advantage of the stochastic\nnature of these methods and minimizes the difference between the predictions of\nmultiple passes of a training sample through the network. We evaluate the\nproposed method on several benchmark datasets.","url_abs":"http://arxiv.org/abs/1606.04586v1","url_pdf":"http://arxiv.org/pdf/1606.04586v1.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":[],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"Ⅱ-model","rank_in_archive_order":14,"of":15,"metrics":{"Accuracy":"82.35"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"Ⅱ-Model","rank_in_archive_order":29,"of":29,"metrics":{"Percentage error":"39.19"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.04586","atlas_url":"https://app.syntology.ai/?focus=1606.04586","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1606.04586"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1606.04586\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1606.04586"},"call":"get_concepts_for_paper(arxiv_id=\"1606.04586\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9952971b0bbdabc6e7f0d5be91296a33a3a275cc6dc42e90dc84ebe957878d3d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}