{"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/guarding-barlow-twins-against-overfitting","title":"Guarding Barlow Twins Against Overfitting with Mixed Samples","arxiv_id":"2312.02151","date":"2023-12-04","proceeding":null,"authors":["Wele Gedara Chaminda Bandara","Celso M. de Melo","Vishal M. Patel"],"abstract":"Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data. The Barlow Twins algorithm, renowned for its widespread adoption and straightforward implementation compared to its counterparts like contrastive learning methods, minimizes feature redundancy while maximizing invariance to common corruptions. Optimizing for the above objective forces the network to learn useful representations, while avoiding noisy or constant features, resulting in improved downstream task performance with limited adaptation. Despite Barlow Twins' proven effectiveness in pre-training, the underlying SSL objective can inadvertently cause feature overfitting due to the lack of strong interaction between the samples unlike the contrastive learning approaches. From our experiments, we observe that optimizing for the Barlow Twins objective doesn't necessarily guarantee sustained improvements in representation quality beyond a certain pre-training phase, and can potentially degrade downstream performance on some datasets. To address this challenge, we introduce Mixed Barlow Twins, which aims to improve sample interaction during Barlow Twins training via linearly interpolated samples. This results in an additional regularization term to the original Barlow Twins objective, assuming linear interpolation in the input space translates to linearly interpolated features in the feature space. Pre-training with this regularization effectively mitigates feature overfitting and further enhances the downstream performance on CIFAR-10, CIFAR-100, TinyImageNet, STL-10, and ImageNet datasets. The code and checkpoints are available at: https://github.com/wgcban/mix-bt.git","url_abs":"https://arxiv.org/abs/2312.02151v1","url_pdf":"https://arxiv.org/pdf/2312.02151v1.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":"guarding-barlow-twins-against-overfitting","repo_url":"https://github.com/wgcban/mix-bt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"barlow-twins","method_name":"Barlow Twins"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-learning-on-stl-10","task":"Self-Supervised Learning","dataset":"STL-10","model":"ResNet50","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"91.70"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-stl-10","task":"Self-Supervised Learning","dataset":"STL-10","model":"ResNet18","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"91.02"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-tinyimagenet","task":"Self-Supervised Learning","dataset":"TinyImageNet","model":"ResNet18","rank_in_archive_order":1,"of":2,"metrics":{"average top-1 classification accuracy":"51.67"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-tinyimagenet","task":"Self-Supervised Learning","dataset":"TinyImageNet","model":"ResNet50","rank_in_archive_order":2,"of":2,"metrics":{"average top-1 classification accuracy":"51.84"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-cifar10","task":"Self-Supervised Learning","dataset":"cifar10","model":"ResNet50","rank_in_archive_order":1,"of":2,"metrics":{"average top-1 classification accuracy":"93.89"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-cifar10","task":"Self-Supervised Learning","dataset":"cifar10","model":"ResNet18","rank_in_archive_order":2,"of":2,"metrics":{"average top-1 classification accuracy":"92.58"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-cifar100","task":"Self-Supervised Learning","dataset":"cifar100","model":"ResNet50","rank_in_archive_order":1,"of":2,"metrics":{"average top-1 classification accuracy":"72.51"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-cifar100","task":"Self-Supervised Learning","dataset":"cifar100","model":"ResNet18","rank_in_archive_order":2,"of":2,"metrics":{"average top-1 classification accuracy":"69.31"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"wgcban/mix-bt","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":"73c8ad715b437dbd79e908bd9c710c9c12eafe635bd0e4c61264ea1b2cd2223b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}