{"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/puzzle-mix-exploiting-saliency-and-local-1","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","arxiv_id":"2009.06962","date":"2020-09-15","proceeding":"ICML 2020 1","authors":["Jang-Hyun Kim","Wonho Choo","Hyun Oh Song"],"abstract":"While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation methods have been recently proposed. However, these approaches mainly focus on creating previously unseen virtual examples and can sometimes provide misleading supervisory signal to the network. To this end, we propose Puzzle Mix, a mixup method for explicitly utilizing the saliency information and the underlying statistics of the natural examples. This leads to an interesting optimization problem alternating between the multi-label objective for optimal mixing mask and saliency discounted optimal transport objective. Our experiments show Puzzle Mix achieves the state of the art generalization and the adversarial robustness results compared to other mixup methods on CIFAR-100, Tiny-ImageNet, and ImageNet datasets. The source code is available at https://github.com/snu-mllab/PuzzleMix.","url_abs":"https://arxiv.org/abs/2009.06962v2","url_pdf":"https://arxiv.org/pdf/2009.06962v2.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":"puzzle-mix-exploiting-saliency-and-local-1","repo_url":"https://github.com/snu-mllab/PuzzleMix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"WRN28-10","rank_in_archive_order":79,"of":211,"metrics":{"Percentage correct":"84.05"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-50","rank_in_archive_order":808,"of":1060,"metrics":{"Top 1 Accuracy":"78.76%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-tiny-imagenet-2","task":"Image Classification","dataset":"Tiny-ImageNet","model":"PreActResNet18","rank_in_archive_order":2,"of":4,"metrics":{"Top 1 Accuracy":"63.48"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-acdc-scribbles","task":"Semantic Segmentation","dataset":"ACDC Scribbles","model":"Puzzle Mix","rank_in_archive_order":6,"of":6,"metrics":{"Dice (Average)":"62.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.06962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.06962"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Borda/pyGCO","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snu-mllab/PuzzleMix","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f0c9a29156911331","entry":"accuracy","repo":"snu-mllab/PuzzleMix","repo_kind":"official","path":"checkpoint/test_robust.py","file_url":"https://github.com/snu-mllab/PuzzleMix/blob/HEAD/checkpoint/test_robust.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0c9a29156911331"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}