{"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/unet-redesigning-skip-connections-to-exploit","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","arxiv_id":"1912.05074","date":"2019-12-11","proceeding":null,"authors":["Zongwei Zhou","Md Mahfuzur Rahman Siddiquee","Nima Tajbakhsh","Jianming Liang"],"abstract":"The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths; and (2) their skip connections impose an unnecessarily restrictive fusion scheme, forcing aggregation only at the same-scale feature maps of the encoder and decoder sub-networks. To overcome these two limitations, we propose UNet++, a new neural architecture for semantic and instance segmentation, by (1) alleviating the unknown network depth with an efficient ensemble of U-Nets of varying depths, which partially share an encoder and co-learn simultaneously using deep supervision; (2) redesigning skip connections to aggregate features of varying semantic scales at the decoder sub-networks, leading to a highly flexible feature fusion scheme; and (3) devising a pruning scheme to accelerate the inference speed of UNet++. We have evaluated UNet++ using six different medical image segmentation datasets, covering multiple imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and electron microscopy (EM), and demonstrating that (1) UNet++ consistently outperforms the baseline models for the task of semantic segmentation across different datasets and backbone architectures; (2) UNet++ enhances segmentation quality of varying-size objects -- an improvement over the fixed-depth U-Net; (3) Mask RCNN++ (Mask R-CNN with UNet++ design) outperforms the original Mask R-CNN for the task of instance segmentation; and (4) pruned UNet++ models achieve significant speedup while showing only modest performance degradation. Our implementation and pre-trained models are available at https://github.com/MrGiovanni/UNetPlusPlus.","url_abs":"https://arxiv.org/abs/1912.05074v2","url_pdf":"https://arxiv.org/pdf/1912.05074v2.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":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/MrGiovanni/UNetPlusPlus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/2023-MindSpore-1/ms-code-118","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/MrGiovanni/Nested-UNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/albertsokol/pneumothorax-detection-unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/alexssanchez/unet-app-pucp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/manuelhz/dissertation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/mrgiovanni/dissertation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/reyvaz/pneumothorax_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/reyvaz/steel-defect-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/rizalmaulanaa/robustness_of_prob_u_net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/sauravmishra1710/UNet-Plus-Plus---Brain-Tumor-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/Burf/tfdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"unet-redesigning-skip-connections-to-exploit","repo_url":"https://github.com/frgfm/Holocron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance 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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"u-net","method_name":"U-Net"},{"method_slug":"unet","method_name":"UNet++"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/brain-image-segmentation-on-brain-tumor","task":"Brain Image Segmentation","dataset":"Brain Tumor","model":"UNet++","rank_in_archive_order":1,"of":1,"metrics":{"IoU":"91.21"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cell","task":"Medical Image Segmentation","dataset":"Cell","model":"UNet++","rank_in_archive_order":1,"of":1,"metrics":{"IoU":"91.21"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-em","task":"Medical Image Segmentation","dataset":"EM","model":"UNet++","rank_in_archive_order":3,"of":3,"metrics":{"IoU":"89.33"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.05074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05074"}},"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/frgfm/Holocron","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/reyvaz/steel-defect-segmentation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/reyvaz/pneumothorax_detection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MrGiovanni/Nested-UNet","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/albertsokol/pneumothorax-detection-unet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-118","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MrGiovanni/UNetPlusPlus","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manuelhz/dissertation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rizalmaulanaa/robustness_of_prob_u_net","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sauravmishra1710/UNet-Plus-Plus---Brain-Tumor-Segmentation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mrgiovanni/dissertation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Burf/tfdetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexssanchez/unet-app-pucp","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"listed":{"samples":7,"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":2,"samples":[{"code_sha256_prefix":"3e9ea4498e4b8a8d","entry":"double_conv","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_training.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_training.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e9ea4498e4b8a8d"}},{"code_sha256_prefix":"d4f3d905e75200e3","entry":"double_conv2","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_++_pruned.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_%2B%2B_pruned.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":"d4f3d905e75200e3"}},{"code_sha256_prefix":"be52c1e7e30a5f3b","entry":"double_conv2","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_++_training.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_%2B%2B_training.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":"be52c1e7e30a5f3b"}},{"code_sha256_prefix":"6b0f999f9e74b1c8","entry":"unetp","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6b0f999f9e74b1c8"}},{"code_sha256_prefix":"42e3369990bb3769","entry":"unetpp","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"42e3369990bb3769"}},{"code_sha256_prefix":"7a968c1589ba71bb","entry":"up3","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_++_pruned.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_%2B%2B_pruned.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":"7a968c1589ba71bb"}},{"code_sha256_prefix":"a6667f374238aad5","entry":"up3","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_++_training.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_%2B%2B_training.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":"a6667f374238aad5"}},{"code_sha256_prefix":"7488d0ba5adf5cd7","entry":"up4","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_++_pruned.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_%2B%2B_pruned.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":"7488d0ba5adf5cd7"}},{"code_sha256_prefix":"22a234a1173d001e","entry":"up4","repo":"manuelhz/dissertation","repo_kind":"listed","path":"BraTS/BraTS_unet_++_training.py","file_url":"https://github.com/manuelhz/dissertation/blob/HEAD/BraTS/BraTS_unet_%2B%2B_training.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":"22a234a1173d001e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}