{"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/alignmix-improving-representation-by","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","arxiv_id":"2103.15375","date":"2021-03-29","proceeding":"CVPR 2022 1","authors":["Shashanka Venkataramanan","Ewa Kijak","Laurent Amsaleg","Yannis Avrithis"],"abstract":"Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more objects into one image, which is more about efficient processing than interpolation. However, how to best interpolate images is not well defined. In this sense, mixup has been connected to autoencoders, because often autoencoders \"interpolate well\", for instance generating an image that continuously deforms into another. In this work, we revisit mixup from the interpolation perspective and introduce AlignMix, where we geometrically align two images in the feature space. The correspondences allow us to interpolate between two sets of features, while keeping the locations of one set. Interestingly, this gives rise to a situation where mixup retains mostly the geometry or pose of one image and the texture of the other, connecting it to style transfer. More than that, we show that an autoencoder can still improve representation learning under mixup, without the classifier ever seeing decoded images. AlignMix outperforms state-of-the-art mixup methods on five different benchmarks.","url_abs":"https://arxiv.org/abs/2103.15375v2","url_pdf":"https://arxiv.org/pdf/2103.15375v2.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":"alignmix-improving-representation-by","repo_url":"https://github.com/shashankvkt/alignmixup_cvpr22","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"alignmix-improving-representation-by","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/representation-learning-on-cifar10","task":"Representation Learning","dataset":"CIFAR10","model":"Resnet 18","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"97.05"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.15375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15375"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/openmixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shashankvkt/alignmixup_cvpr22","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"imagenet/models/resnet.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/imagenet/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"cifar10_100/models/WideResnet.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/cifar10_100/models/WideResnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00e569acd6b45ef0"}},{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"cifar10_100/models/resnet.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/cifar10_100/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"757642f60b4ddb4a","entry":"cosine_scheduler","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"imagenet/utils/util.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/imagenet/utils/util.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":"757642f60b4ddb4a"}},{"code_sha256_prefix":"aa3f975a6414573b","entry":"mixup_process","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"cifar10_100/models/resnet18_classifier.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/cifar10_100/models/resnet18_classifier.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":"aa3f975a6414573b"}},{"code_sha256_prefix":"de7aea7428f71cf9","entry":"subset_of_ImageNet_train_split","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"imagenet/utils/util.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/imagenet/utils/util.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":"de7aea7428f71cf9"}},{"code_sha256_prefix":"1bcad658b2d372fc","entry":"wrn28_10","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"cifar10_100/models/WideResnet.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/cifar10_100/models/WideResnet.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":"1bcad658b2d372fc"}},{"code_sha256_prefix":"f971438664b96268","entry":"wrn28_2","repo":"shashankvkt/alignmixup_cvpr22","repo_kind":"official","path":"cifar10_100/models/WideResnet.py","file_url":"https://github.com/shashankvkt/alignmixup_cvpr22/blob/HEAD/cifar10_100/models/WideResnet.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":"f971438664b96268"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}