{"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/sumix-mixup-with-semantic-and-uncertain","title":"SUMix: Mixup with Semantic and Uncertain Information","arxiv_id":"2407.07805","date":"2024-07-10","proceeding":null,"authors":["Huafeng Qin","Xin Jin","Hongyu Zhu","Hongchao Liao","Mounîm A. El-Yacoubi","Xinbo Gao"],"abstract":"Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image with patches from another to generate the mixed image. Similarly, the corresponding labels are linearly combined by a fixed ratio $\\lambda$ by l. The objects in two images may be overlapped during the mixing process, so some semantic information is corrupted in the mixed samples. In this case, the mixed image does not match the mixed label information. Besides, such a label may mislead the deep learning model training, which results in poor performance. To solve this problem, we proposed a novel approach named SUMix to learn the mixing ratio as well as the uncertainty for the mixed samples during the training process. First, we design a learnable similarity function to compute an accurate mix ratio. Second, an approach is investigated as a regularized term to model the uncertainty of the mixed samples. We conduct experiments on five image benchmarks, and extensive experimental results imply that our method is capable of improving the performance of classifiers with different cutting-based mixup approaches. The source code is available at https://github.com/JinXins/SUMix.","url_abs":"https://arxiv.org/abs/2407.07805v4","url_pdf":"https://arxiv.org/pdf/2407.07805v4.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":"sumix-mixup-with-semantic-and-uncertain","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sumix-mixup-with-semantic-and-uncertain","repo_url":"https://github.com/jinxins/sumix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"cutmix","method_name":"CutMix"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.07805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07805"}},"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/jinxins/sumix","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":"9d9b0c55c72acf25","entry":"annealing_cos","repo":"jinxins/sumix","repo_kind":"official","path":"openmixup/core/hooks/addtional_scheduler.py","file_url":"https://github.com/jinxins/sumix/blob/HEAD/openmixup/core/hooks/addtional_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d9b0c55c72acf25"}},{"code_sha256_prefix":"b46e88c7adaa8b7b","entry":"get_position_from_periods","repo":"jinxins/sumix","repo_kind":"official","path":"openmixup/core/hooks/addtional_scheduler.py","file_url":"https://github.com/jinxins/sumix/blob/HEAD/openmixup/core/hooks/addtional_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b46e88c7adaa8b7b"}},{"code_sha256_prefix":"c0b7dd157b87fa80","entry":"get_random_weights","repo":"jinxins/sumix","repo_kind":"official","path":"openmixup/utils/loss_landscape_utils.py","file_url":"https://github.com/jinxins/sumix/blob/HEAD/openmixup/utils/loss_landscape_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0b7dd157b87fa80"}},{"code_sha256_prefix":"5fa87577ccee9cca","entry":"get_weights","repo":"jinxins/sumix","repo_kind":"official","path":"openmixup/utils/loss_landscape_utils.py","file_url":"https://github.com/jinxins/sumix/blob/HEAD/openmixup/utils/loss_landscape_utils.py","link_basis":"harvester_set","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":"5fa87577ccee9cca"}},{"code_sha256_prefix":"0a0d8afa0c9cf088","entry":"knn_classifier","repo":"jinxins/sumix","repo_kind":"official","path":"benchmarks/classification/knn_imagenet/knn_classifier.py","file_url":"https://github.com/jinxins/sumix/blob/HEAD/benchmarks/classification/knn_imagenet/knn_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":"0a0d8afa0c9cf088"}},{"code_sha256_prefix":"0d11ac9cea6805a3","entry":"read_list","repo":"jinxins/sumix","repo_kind":"official","path":"openmixup/utils/loss_landscape_utils.py","file_url":"https://github.com/jinxins/sumix/blob/HEAD/openmixup/utils/loss_landscape_utils.py","link_basis":"harvester_set","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":"0d11ac9cea6805a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}