{"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/dlme-deep-local-flatness-manifold-embedding","title":"DLME: Deep Local-flatness Manifold Embedding","arxiv_id":"2207.03160","date":"2022-07-07","proceeding":null,"authors":["Zelin Zang","Siyuan Li","Di wu","Ge Wang","Lei Shang","Baigui Sun","Hao Li","Stan Z. Li"],"abstract":"Manifold learning (ML) aims to seek low-dimensional embedding from high-dimensional data. The problem is challenging on real-world datasets, especially with under-sampling data, and we find that previous methods perform poorly in this case. Generally, ML methods first transform input data into a low-dimensional embedding space to maintain the data's geometric structure and subsequently perform downstream tasks therein. The poor local connectivity of under-sampling data in the former step and inappropriate optimization objectives in the latter step leads to two problems: structural distortion and underconstrained embedding. This paper proposes a novel ML framework named Deep Local-flatness Manifold Embedding (DLME) to solve these problems. The proposed DLME constructs semantic manifolds by data augmentation and overcomes the structural distortion problem using a smoothness constrained based on a local flatness assumption about the manifold. To overcome the underconstrained embedding problem, we design a loss and theoretically demonstrate that it leads to a more suitable embedding based on the local flatness. Experiments on three types of datasets (toy, biological, and image) for various downstream tasks (classification, clustering, and visualization) show that our proposed DLME outperforms state-of-the-art ML and contrastive learning methods.","url_abs":"https://arxiv.org/abs/2207.03160v2","url_pdf":"https://arxiv.org/pdf/2207.03160v2.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":"dlme-deep-local-flatness-manifold-embedding","repo_url":"https://github.com/zangzelin/code_ECCV2022_DLME","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"dlme-deep-local-flatness-manifold-embedding","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"DLME (ResNet-18, linear)","rank_in_archive_order":193,"of":265,"metrics":{"Percentage correct":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"DLME (ResNet-18, linear)","rank_in_archive_order":190,"of":211,"metrics":{"Percentage correct":"66.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-100","task":"Image Classification","dataset":"ImageNet-100 (TEMI Split)","model":"DLME (ResNet-50, linear)","rank_in_archive_order":2,"of":2,"metrics":{"Percentage correct":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"DLME (ResNet-50, linear)","rank_in_archive_order":35,"of":117,"metrics":{"Percentage correct":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-tiny-imagenet-2","task":"Image Classification","dataset":"Tiny-ImageNet","model":"DLME (ResNet-18, linear)","rank_in_archive_order":3,"of":4,"metrics":{"Top 1 Accuracy":"44.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.03160"}},"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/zangzelin/code_ECCV2022_DLME","reach":null}],"summary":{"ran":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":"57bf8a530a89bd9c","entry":"MyLoss","repo":"zangzelin/code_ECCV2022_DLME","repo_kind":"official","path":"Loss/dmt_loss_aug.py","file_url":"https://github.com/zangzelin/code_ECCV2022_DLME/blob/HEAD/Loss/dmt_loss_aug.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"57bf8a530a89bd9c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}