{"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/sagemix-saliency-guided-mixup-for-point","title":"SageMix: Saliency-Guided Mixup for Point Clouds","arxiv_id":"2210.06944","date":"2022-10-13","proceeding":null,"authors":["Sanghyeok Lee","Minkyu Jeon","Injae Kim","Yunyang Xiong","Hyunwoo J. Kim"],"abstract":"Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity. Also, recent studies of saliency-aware Mixup in the image domain show that preserving discriminative parts is beneficial to improving the generalization performance. However, these Mixup-based data augmentations are underexplored in 3D vision, especially in point clouds. In this paper, we propose SageMix, a saliency-guided Mixup for point clouds to preserve salient local structures. Specifically, we extract salient regions from two point clouds and smoothly combine them into one continuous shape. With a simple sequential sampling by re-weighted saliency scores, SageMix preserves the local structure of salient regions. Extensive experiments demonstrate that the proposed method consistently outperforms existing Mixup methods in various benchmark point cloud datasets. With PointNet++, our method achieves an accuracy gain of 2.6% and 4.0% over standard training in 3D Warehouse dataset (MN40) and ScanObjectNN, respectively. In addition to generalization performance, SageMix improves robustness and uncertainty calibration. Moreover, when adopting our method to various tasks including part segmentation and standard 2D image classification, our method achieves competitive performance.","url_abs":"https://arxiv.org/abs/2210.06944v1","url_pdf":"https://arxiv.org/pdf/2210.06944v1.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":"sagemix-saliency-guided-mixup-for-point","repo_url":"https://github.com/mlvlab/SageMix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-point-cloud-data-augmentation","task_name":"3D Point Cloud Data Augmentation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"PointNet++ + SageMix","rank_in_archive_order":44,"of":67,"metrics":{"Instance Average IoU":"85.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"DGCNN + SageMix","rank_in_archive_order":48,"of":67,"metrics":{"Instance Average IoU":"85.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"DGCNN + SageMix","rank_in_archive_order":55,"of":111,"metrics":{"Overall Accuracy":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"PointNet++ + SageMix","rank_in_archive_order":68,"of":111,"metrics":{"Overall Accuracy":"93.3"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"PointNet + SageMix","rank_in_archive_order":103,"of":111,"metrics":{"Overall Accuracy":"90.3"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"PointNet++ + SageMix","rank_in_archive_order":61,"of":77,"metrics":{"Overall Accuracy":"83.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"DGCNN + SageMix","rank_in_archive_order":62,"of":77,"metrics":{"Overall Accuracy":"83.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"PreActResNet-18 + SageMix","rank_in_archive_order":131,"of":211,"metrics":{"Percentage correct":"80.16"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.06944","atlas_url":"https://app.syntology.ai/?focus=2210.06944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06944"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/mlvlab/SageMix","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":"5839f5fcd5e18e7f","entry":"SageMix","repo":"mlvlab/SageMix","repo_kind":"official","path":"pointcloud/SageMix.py","file_url":"https://github.com/mlvlab/SageMix/blob/HEAD/pointcloud/SageMix.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":"5839f5fcd5e18e7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}