{"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/uctransnet-rethinking-the-skip-connections-in","title":"UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer","arxiv_id":"2109.04335","date":"2021-09-09","proceeding":null,"authors":["Haonan Wang","Peng Cao","Jiaqi Wang","Osmar R. Zaiane"],"abstract":"Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UCTransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism. Specifically, the CTrans module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity. Hence, the proposed connection consisting of the CCT and CCA is able to replace the original skip connection to solve the semantic gaps for an accurate automatic medical image segmentation. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the state-of-the-art for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework. Code: https://github.com/McGregorWwww/UCTransNet.","url_abs":"https://arxiv.org/abs/2109.04335v3","url_pdf":"https://arxiv.org/pdf/2109.04335v3.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":"uctransnet-rethinking-the-skip-connections-in","repo_url":"https://github.com/mcgregorwwww/uctransnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"uctransnet-rethinking-the-skip-connections-in","repo_url":"https://github.com/lucidrains/imagen-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"uctransnet-rethinking-the-skip-connections-in","repo_url":"https://github.com/2023-MindSpore-1/ms-code-6/tree/main/cct","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"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"},{"task_slug":"unet-segmentation","task_name":"UNET 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":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cct","method_name":"CCT"},{"method_slug":"channel-wise-cross-attention","method_name":"Channel-wise Cross Attention"},{"method_slug":"channel-wise-cross-fusion-transformer","method_name":"Channel-wise Cross Fusion Transformer"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"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":"max-pooling","method_name":"Max Pooling"},{"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":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"u-net","method_name":"U-Net"},{"method_slug":"uctransnet","method_name":"UCTransNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"channel-wise-cross-attention","name":"Channel-wise Cross Attention","full_name":"Channel-wise Cross Attention"}],"results":[{"leaderboard":"/sota/medical-image-segmentation-on-glas","task":"Medical Image Segmentation","dataset":"GlaS","model":"UCTransNet","rank_in_archive_order":3,"of":10,"metrics":{"Dice":"90.18","F1":"90.18","IoU":"82.96"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-glas","task":"Medical Image Segmentation","dataset":"GlaS","model":"U-Net++","rank_in_archive_order":5,"of":10,"metrics":{"Dice":"87.56","F1":"87.56","IoU":"79.13"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-glas","task":"Medical Image Segmentation","dataset":"GlaS","model":"U-Net","rank_in_archive_order":6,"of":10,"metrics":{"Dice":"85.45","F1":"85.45","IoU":"74.78"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-synapse-multi","task":"Medical Image Segmentation","dataset":"Synapse multi-organ CT","model":"UCTransNet","rank_in_archive_order":22,"of":23,"metrics":{"Avg DSC":"78.99","Avg HD":"30.29"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.04335","atlas_url":"https://app.syntology.ai/?focus=2109.04335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04335"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-6/tree/main/cct","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mcgregorwwww/uctransnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/imagen-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":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":"43ef84aa490c7681","entry":"logger_config","repo":"mcgregorwwww/uctransnet","repo_kind":"official","path":"train_model.py","file_url":"https://github.com/mcgregorwwww/uctransnet/blob/HEAD/train_model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43ef84aa490c7681"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}