{"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/segformer3d-an-efficient-transformer-for-3d","title":"SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation","arxiv_id":"2404.10156","date":"2024-04-15","proceeding":null,"authors":["Shehan Perera","Pouyan Navard","Alper Yilmaz"],"abstract":"The adoption of Vision Transformers (ViTs) based architectures represents a significant advancement in 3D Medical Image (MI) segmentation, surpassing traditional Convolutional Neural Network (CNN) models by enhancing global contextual understanding. While this paradigm shift has significantly enhanced 3D segmentation performance, state-of-the-art architectures require extremely large and complex architectures with large scale computing resources for training and deployment. Furthermore, in the context of limited datasets, often encountered in medical imaging, larger models can present hurdles in both model generalization and convergence. In response to these challenges and to demonstrate that lightweight models are a valuable area of research in 3D medical imaging, we present SegFormer3D, a hierarchical Transformer that calculates attention across multiscale volumetric features. Additionally, SegFormer3D avoids complex decoders and uses an all-MLP decoder to aggregate local and global attention features to produce highly accurate segmentation masks. The proposed memory efficient Transformer preserves the performance characteristics of a significantly larger model in a compact design. SegFormer3D democratizes deep learning for 3D medical image segmentation by offering a model with 33x less parameters and a 13x reduction in GFLOPS compared to the current state-of-the-art (SOTA). We benchmark SegFormer3D against the current SOTA models on three widely used datasets Synapse, BRaTs, and ACDC, achieving competitive results. Code: https://github.com/OSUPCVLab/SegFormer3D.git","url_abs":"https://arxiv.org/abs/2404.10156v2","url_pdf":"https://arxiv.org/pdf/2404.10156v2.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":"segformer3d-an-efficient-transformer-for-3d","repo_url":"https://github.com/osupcvlab/segformer3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"segformer3d-an-efficient-transformer-for-3d","repo_url":"https://github.com/MindSpore-scientific/code-7/tree/main/SegFormer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"brain-tumor-segmentation","task_name":"Brain Tumor Segmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/brain-tumor-segmentation-on-brats-2017-val","task":"Brain Tumor Segmentation","dataset":"BRATS-2017 val","model":"SegFormer3D","rank_in_archive_order":1,"of":3,"metrics":{"Dice Score":"0.9096"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-automatic","task":"Medical Image Segmentation","dataset":"Automatic Cardiac Diagnosis Challenge (ACDC)","model":"SegFormer3D","rank_in_archive_order":14,"of":20,"metrics":{"Avg DSC":"90.96"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-synapse-multi","task":"Medical Image Segmentation","dataset":"Synapse multi-organ CT","model":"SegFormer3D","rank_in_archive_order":14,"of":23,"metrics":{"Avg DSC":"82.15"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.10156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10156"}},"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/osupcvlab/segformer3d","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-7/tree/main/SegFormer","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"e313e39a05423199","entry":"animate","repo":"osupcvlab/segformer3d","repo_kind":"official","path":"data/brats2017_seg/brats2017_raw_data/brats2017_seg_preprocess.py","file_url":"https://github.com/osupcvlab/segformer3d/blob/HEAD/data/brats2017_seg/brats2017_raw_data/brats2017_seg_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e313e39a05423199"}},{"code_sha256_prefix":"7b1a52cd917b1f5d","entry":"load_config","repo":"osupcvlab/segformer3d","repo_kind":"official","path":"experiments/brats_2017/template_experiment/run_experiment.py","file_url":"https://github.com/osupcvlab/segformer3d/blob/HEAD/experiments/brats_2017/template_experiment/run_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7b1a52cd917b1f5d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}