{"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/on-mixup-training-improved-calibration-and","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","arxiv_id":"1905.11001","date":"2019-05-27","proceeding":"NeurIPS 2019 12","authors":["Sunil Thulasidasan","Gopinath Chennupati","Jeff Bilmes","Tanmoy Bhattacharya","Sarah Michalak"],"abstract":"Mixup~\\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to implement, it has been shown to be a surprisingly effective method of data augmentation for image classification: DNNs trained with mixup show noticeable gains in classification performance on a number of image classification benchmarks. In this work, we discuss a hitherto untouched aspect of mixup training -- the calibration and predictive uncertainty of models trained with mixup. We find that DNNs trained with mixup are significantly better calibrated -- i.e., the predicted softmax scores are much better indicators of the actual likelihood of a correct prediction -- than DNNs trained in the regular fashion. We conduct experiments on a number of image classification architectures and datasets -- including large-scale datasets like ImageNet -- and find this to be the case. Additionally, we find that merely mixing features does not result in the same calibration benefit and that the label smoothing in mixup training plays a significant role in improving calibration. Finally, we also observe that mixup-trained DNNs are less prone to over-confident predictions on out-of-distribution and random-noise data. We conclude that the typical overconfidence seen in neural networks, even on in-distribution data is likely a consequence of training with hard labels, suggesting that mixup be employed for classification tasks where predictive uncertainty is a significant concern.","url_abs":"https://arxiv.org/abs/1905.11001v5","url_pdf":"https://arxiv.org/pdf/1905.11001v5.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":"on-mixup-training-improved-calibration-and","repo_url":"https://github.com/MacroMayhem/OnMixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"on-mixup-training-improved-calibration-and","repo_url":"https://github.com/paganpasta/onmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"mixup","method_name":"Mixup"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-stl-10","task":"Out-of-Distribution Detection","dataset":"STL-10","model":"Mixup (Gaussian)","rank_in_archive_order":1,"of":6,"metrics":{"Percentage correct":"95.93"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-stl-10","task":"Out-of-Distribution Detection","dataset":"STL-10","model":"Mixup (Imagenet)","rank_in_archive_order":2,"of":6,"metrics":{"Percentage correct":"83.28"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-stl-10","task":"Out-of-Distribution Detection","dataset":"STL-10","model":"Baseline (Imagenet)","rank_in_archive_order":3,"of":6,"metrics":{"Percentage correct":"80.57"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-stl-10","task":"Out-of-Distribution Detection","dataset":"STL-10","model":"Dropout(Imagenet)","rank_in_archive_order":4,"of":6,"metrics":{"Percentage correct":"78.93"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-stl-10","task":"Out-of-Distribution Detection","dataset":"STL-10","model":"Baseline (Gaussian)","rank_in_archive_order":5,"of":6,"metrics":{"Percentage correct":"73.28"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-stl-10","task":"Out-of-Distribution Detection","dataset":"STL-10","model":"Dropout(Gaussian)","rank_in_archive_order":6,"of":6,"metrics":{"Percentage correct":"70.57"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.11001","atlas_url":"https://app.syntology.ai/?focus=1905.11001","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":"1905.11001"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1905.11001\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1905.11001"},"call":"get_concepts_for_paper(arxiv_id=\"1905.11001\")"}],"by_repo":[{"repo":"MacroMayhem/OnMixup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"paganpasta/onmixup","kind":"listed","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":"c3eced400c02fed99f6844ae3c9cc122fa977f757b09ffbd280ff4059258f0bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}