{"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/mixmo-mixing-multiple-inputs-for-multiple","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","arxiv_id":"2103.06132","date":"2021-03-10","proceeding":"ICCV 2021 10","authors":["Alexandre Rame","Remy Sun","Matthieu Cord"],"abstract":"Recent strategies achieved ensembling \"for free\" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs simultaneously provided. However, the question of how to best mix these multiple inputs has not been studied so far. In this paper, we introduce MixMo, a new generalized framework for learning multi-input multi-output deep subnetworks. Our key motivation is to replace the suboptimal summing operation hidden in previous approaches by a more appropriate mixing mechanism. For that purpose, we draw inspiration from successful mixed sample data augmentations. We show that binary mixing in features - particularly with rectangular patches from CutMix - enhances results by making subnetworks stronger and more diverse. We improve state of the art for image classification on CIFAR-100 and Tiny ImageNet datasets. Our easy to implement models notably outperform data augmented deep ensembles, without the inference and memory overheads. As we operate in features and simply better leverage the expressiveness of large networks, we open a new line of research complementary to previous works.","url_abs":"https://arxiv.org/abs/2103.06132v3","url_pdf":"https://arxiv.org/pdf/2103.06132v3.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":"mixmo-mixing-multiple-inputs-for-multiple","repo_url":"https://github.com/alexrame/mixmo-pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"cutmix","method_name":"CutMix"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"WRN-28-10","rank_in_archive_order":72,"of":265,"metrics":{"Percentage correct":"97.73"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"WRN-28-10 * 3","rank_in_archive_order":50,"of":211,"metrics":{"Percentage correct":"86.81"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"WRN-28-10","rank_in_archive_order":58,"of":211,"metrics":{"Percentage correct":"85.77"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-tiny-imagenet-1","task":"Image Classification","dataset":"Tiny ImageNet Classification","model":"PreActResNet-18-3","rank_in_archive_order":16,"of":23,"metrics":{"Validation Acc":"70.24%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.06132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06132"}},"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/alexrame/mixmo-pytorch","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"a49c44a090d15103","entry":"mix_manifolds","repo":"alexrame/mixmo-pytorch","repo_kind":"official","path":"mixmo/augmentations/mixing_blocks.py","file_url":"https://github.com/alexrame/mixmo-pytorch/blob/HEAD/mixmo/augmentations/mixing_blocks.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a49c44a090d15103"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}