Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/27972
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lei, T | - |
dc.contributor.author | Sun, R | - |
dc.contributor.author | Wang, X | - |
dc.contributor.author | Wang, Y | - |
dc.contributor.author | He, X | - |
dc.contributor.author | Nandi, A | - |
dc.coverage.spatial | Macao, S.A.R. | - |
dc.date.accessioned | 2024-01-06T12:40:39Z | - |
dc.date.available | 2024-01-06T12:40:39Z | - |
dc.date.issued | 2023-08-19 | - |
dc.identifier | ORCID iD: Asoke Nandi https://orcid.org/0000-0001-6248-2875 | - |
dc.identifier | arXiv:2306.03373v2 [eess.IV] | - |
dc.identifier.citation | Lei, T. et al. (2023) 'CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation', Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, Macao, S.A.R., 19-25 August,, pp. 1017 - 1025. Available at: https://www.ijcai.org/proceedings/2023/113. | en_US |
dc.identifier.isbn | 978-1-956792-03-4 | - |
dc.identifier.issn | 1045-0823 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/27972 | - |
dc.description | The code is publicly available at: https://github.com/SR0920/CiT-Net . | en_US |
dc.description | The conference paper archived on this institutional repository is the second, revised version made available at arXiv:2306.03373v2 [eess.IV], [v2] Wed, 20 Dec 2023 02:42:13 UTC (3,309 KB), https://arxiv.org/abs/2306.03373 under an arXiv non-exclusive license (https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html). | - |
dc.description.abstract | The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features using vanilla convolution, it cannot achieve adaptive feature learning. Second, although a Transformer branch can capture the global features, it ignores the channel and cross-dimensional self-attention, resulting in a low segmentation accuracy on complex-content images. To address these challenges, we propose a novel hybrid architecture of convolutional neural networks hand in hand with vision Transformers (CiT-Net) for medical image segmentation. Our network has two advantages. First, we design a dynamic deformable convolution and apply it to the CNNs branch, which overcomes the weak feature extraction ability due to fixed-size convolution kernels and the stiff design of sharing kernel parameters among different inputs. Second, we design a shifted-window adaptive complementary attention module and a compact convolutional projection. We apply them to the Transformer branch to learn the cross-dimensional long-term dependency for medical images. Experimental results show that our CiT-Net provides better medical image segmentation results than popular SOTA methods. Besides, our CiT-Net requires lower parameters and less computational costs and does not rely on pre-training. | en_US |
dc.description.sponsorship | National Natural Science Foundation of China under Grants 62271296, 62201334 and 62201452, in part by the Natural Science Basic Research Program of Shaanxi under Grant 2021JC-47, and in part by the Key Research and Development Program of Shaanxi under Grants 2022GY-436 and 2021ZDLGY08-07. | en_US |
dc.format.extent | 1017 - 1025 | - |
dc.format.medium | Print-Electronic | - |
dc.language | English | - |
dc.language.iso | en_US | en_US |
dc.publisher | International Joint Conference on Artificial Intelligence (IJCAI) | en_US |
dc.relation.uri | https://github.com/SR0920/CiT-Net | - |
dc.relation.uri | https://www.ijcai.org/proceedings/2023/ | - |
dc.relation.uri | https://arxiv.org/abs/2306.03373 | - |
dc.rights | The conference paper archived on this institutional repository is the second, revised version made available at arXiv:2306.03373v2 [eess.IV], [v2] Wed, 20 Dec 2023 02:42:13 UTC (3,309 KB), https://arxiv.org/abs/2306.03373 under an arXiv non-exclusive license (https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html). | - |
dc.rights.uri | https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html | - |
dc.source | 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023) | - |
dc.source | 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023) | - |
dc.title | CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.24963/ijcai.2023/113 | - |
dc.relation.isPartOf | IJCAI International Joint Conference on Artificial Intelligence | - |
pubs.finish-date | 2023-08-25 | - |
pubs.finish-date | 2023-08-25 | - |
pubs.publication-status | Published | - |
pubs.start-date | 2023-08-19 | - |
pubs.start-date | 2023-08-19 | - |
pubs.volume | 2023-August | - |
dc.rights.holder | The Authors | - |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | The conference paper archived on this institutional repository is the second, revised version made available at arXiv:2306.03373v2 [eess.IV], [v2] Wed, 20 Dec 2023 02:42:13 UTC (3,309 KB), https://arxiv.org/abs/2306.03373 under an arXiv non-exclusive license (https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html). | 5.13 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.