{"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/a-bayesian-data-augmentation-approach-for","title":"A Bayesian Data Augmentation Approach for Learning Deep Models","arxiv_id":"1710.10564","date":"2017-10-29","proceeding":"NeurIPS 2017 12","authors":["Toan Tran","Trung Pham","Gustavo Carneiro","Lyle Palmer","Ian Reid"],"abstract":"Data augmentation is an essential part of the training process applied to\ndeep learning models. The motivation is that a robust training process for deep\nlearning models depends on large annotated datasets, which are expensive to be\nacquired, stored and processed. Therefore a reasonable alternative is to be\nable to automatically generate new annotated training samples using a process\nknown as data augmentation. The dominant data augmentation approach in the\nfield assumes that new training samples can be obtained via random geometric or\nappearance transformations applied to annotated training samples, but this is a\nstrong assumption because it is unclear if this is a reliable generative model\nfor producing new training samples. In this paper, we provide a novel Bayesian\nformulation to data augmentation, where new annotated training points are\ntreated as missing variables and generated based on the distribution learned\nfrom the training set. For learning, we introduce a theoretically sound\nalgorithm --- generalised Monte Carlo expectation maximisation, and demonstrate\none possible implementation via an extension of the Generative Adversarial\nNetwork (GAN). Classification results on MNIST, CIFAR-10 and CIFAR-100 show the\nbetter performance of our proposed method compared to the current dominant data\naugmentation approach mentioned above --- the results also show that our\napproach produces better classification results than similar GAN models.","url_abs":"http://arxiv.org/abs/1710.10564v1","url_pdf":"http://arxiv.org/pdf/1710.10564v1.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":"a-bayesian-data-augmentation-approach-for","repo_url":"https://github.com/toantm/keras-bda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.10564","atlas_url":"https://app.syntology.ai/?focus=1710.10564","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":"1710.10564"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1710.10564\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1710.10564"},"call":"get_concepts_for_paper(arxiv_id=\"1710.10564\")"}],"by_repo":[{"repo":"toantm/keras-bda","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b8d4fe6bb4bb4da8499758713a12df223af2455887b4666073a39b09161b1d8d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}