{"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/hyperdense-net-a-hyper-densely-connected-cnn","title":"HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation","arxiv_id":"1804.02967","date":"2018-04-09","proceeding":null,"authors":["Jose Dolz","Karthik Gopinath","Jing Yuan","Herve Lombaert","Christian Desrosiers","Ismail Ben Ayed"],"abstract":"Recently, dense connections have attracted substantial attention in computer\nvision because they facilitate gradient flow and implicit deep supervision\nduring training. Particularly, DenseNet, which connects each layer to every\nother layer in a feed-forward fashion, has shown impressive performances in\nnatural image classification tasks. We propose HyperDenseNet, a 3D fully\nconvolutional neural network that extends the definition of dense connectivity\nto multi-modal segmentation problems. Each imaging modality has a path, and\ndense connections occur not only between the pairs of layers within the same\npath, but also between those across different paths. This contrasts with the\nexisting multi-modal CNN approaches, in which modeling several modalities\nrelies entirely on a single joint layer (or level of abstraction) for fusion,\ntypically either at the input or at the output of the network. Therefore, the\nproposed network has total freedom to learn more complex combinations between\nthe modalities, within and in-between all the levels of abstraction, which\nincreases significantly the learning representation. We report extensive\nevaluations over two different and highly competitive multi-modal brain tissue\nsegmentation challenges, iSEG 2017 and MRBrainS 2013, with the former focusing\non 6-month infant data and the latter on adult images. HyperDenseNet yielded\nsignificant improvements over many state-of-the-art segmentation networks,\nranking at the top on both benchmarks. We further provide a comprehensive\nexperimental analysis of features re-use, which confirms the importance of\nhyper-dense connections in multi-modal representation learning. Our code is\npublicly available at https://www.github.com/josedolz/HyperDenseNet.","url_abs":"http://arxiv.org/abs/1804.02967v2","url_pdf":"http://arxiv.org/pdf/1804.02967v2.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":"hyperdense-net-a-hyper-densely-connected-cnn","repo_url":"https://github.com/josedolz/HyperDenseNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"hyperdense-net-a-hyper-densely-connected-cnn","repo_url":"https://github.com/black0017/MedicalZooPytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hyperdense-net-a-hyper-densely-connected-cnn","repo_url":"https://github.com/josedolz/HyperDenseNet_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"brain-segmentation","task_name":"Brain Segmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"multi-modal-image-segmentation","task_name":"Multi-modal image segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"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":"hyperdensenet","method_name":"HyperDenseNet"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"hyperdensenet","name":"HyperDenseNet","full_name":"HyperDenseNet"}],"results":[{"leaderboard":"/sota/medical-image-segmentation-on-iseg-2017","task":"Medical Image Segmentation","dataset":"iSEG 2017 Challenge","model":"HyperDenseNet","rank_in_archive_order":1,"of":1,"metrics":{"Dice Score":"0.9257"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.02967"}},"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/josedolz/HyperDenseNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/josedolz/HyperDenseNet_pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/black0017/MedicalZooPytorch","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":"12bd8c76be314132","entry":"conv","repo":"black0017/MedicalZooPytorch","repo_kind":"listed","path":"lib/medzoo/HyperDensenet.py","file_url":"https://github.com/black0017/MedicalZooPytorch/blob/HEAD/lib/medzoo/HyperDensenet.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12bd8c76be314132"}},{"code_sha256_prefix":"b44139feb813153e","entry":"conv_block","repo":"black0017/MedicalZooPytorch","repo_kind":"listed","path":"lib/medzoo/HyperDensenet.py","file_url":"https://github.com/black0017/MedicalZooPytorch/blob/HEAD/lib/medzoo/HyperDensenet.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b44139feb813153e"}},{"code_sha256_prefix":"da8f12a015e42861","entry":"upSampleConv_Res","repo":"black0017/MedicalZooPytorch","repo_kind":"listed","path":"lib/medzoo/HyperDensenet.py","file_url":"https://github.com/black0017/MedicalZooPytorch/blob/HEAD/lib/medzoo/HyperDensenet.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da8f12a015e42861"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}