Recalibrating Fully Convolutional Networks With Spatial and Channel “Squeeze and Excitation” Blocks
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
In a wide range of semantic segmentation tasks, fully convolutional neural networks (F-CNNs) have been successfully leveraged to achieve the state-of-the-art performance. Architectural innovations of F-CNNs have mainly been on improving spatial encoding or network connectivity to aid gradient flow. In this paper, we aim toward an alternate direction of recalibrating the learned feature maps adaptively, boosting meaningful features while suppressing weak ones. The recalibration is achieved by simple computational blocks that can be easily integrated in F-CNNs architectures. We draw our inspiration from the recently proposed "squeeze and excitation" (SE) modules for channel recalibration for image classification. Toward this end, we introduce three variants of SE modules for segmentation: 1) squeezing spatially and exciting channel wise; 2) squeezing channel wise and exciting spatially; and 3) joint spatial and channel SE. We effectively incorporate the proposed SE blocks in three state-of-the-art F-CNNs and demonstrate a consistent improvement of segmentation accuracy on three challenging benchmark datasets. Importantly, SE blocks only lead to a minimal increase in model complexity of about 1.5%, while the Dice score increases by 4%-9% in the case of U-Net. Hence, we believe that SE blocks can be an integral part of future F-CNN architectures.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Roy et al. [137, 138] presented three types of modules: (1) channel squeeze and excitation with concurrent channels (scSE); (2) exciting spatially and squeezing channel-wise (sSE); (3) exciting channel-wise and squeezing spatially (cSE).”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [138]
In the citing paper
“To make the work valid for segmentation tasks, Roy et al. [137, 138] expanded Hu et al. [134] effort by adding the influence of spatial information to the channel information.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [138]
In the citing paper
“Dual Attention Network (DAN) [20] simultaneously utilizes Non-Local based channel and spatial attention for semantic segmentation.”
From DanHAR: Dual Attention Network for multimodal human activity recognition using wearable sensors (2021) · cites this paper as [20]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
Research works printed but not linked: 1
- Landman, MICCAI 2012 workshop on multi-atlas labeling
Cited by
Items 601–631 of 631
Penjarla, N. K., Tadi, V. R., Sonti, K., Akumalla, S., Prasanthi, R., & Srinivas1, K. (2026) · Research Square · doi:10.21203/rs.3.rs-9976437/v1
Wu, X., Lan, Y., Han, L., & Wang, P. Y. (2026) · Tomography · doi:10.3390/tomography12070093
RCSCAC-Net: a robust image tampering localization network for Gaussian-blurred forgery images
Shan, W., Guo, J., Si, J., Cao, J., Yang, Y., & Su, H. A. K. S. O. O. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.105020
A Hybrid U-Shaped Deep Learning Network for Intracerebral Hemorrhage Segmentation in CT Scans
Deng, M., Jiazuo, Y., Wu, Q., Liang, S., Liang, H., & Tang, H. (2026) · Sensors · doi:10.3390/s26134164
Dong, X., Li, J., Shang, K., Chen, Y., & Liu, M. Y. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3709734
Towards Semantic Redundancy Mitigation for Medical Image Segmentation
Tong, J., Ma, L. L., Ji, Y., Wu, S., Hu, Z., Liu, K., Ding, Y., & Lu, H. Y. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582394
Ye, K., Miao, J., Wang, J., Huang, Y., & Lu, P. (2026) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2026-99-1628
Anatomically constrained hierarchical post-processing for pediatric brain tumor segmentation
Yoon, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-63071-4
Regularized Channel-Attentive Adversarial Learning for Unpaired Image TranslationPreprint
Gao, W., Yu, X., Rong, X., & Sun, L. (2026) · Research Square · doi:10.21203/rs.3.rs-10080208/v1
Qi, L., Zhou, C., Zhao, M., Wu, B., Ye, Q., Li, M., Xie, W., Zhao, S., & Zhang, K. (2026) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2026.112279
A multi-resolution dual-path network with domain separated attention for medical image segmentation
Zhu, S., Li, Y., Wang, C., Mao, T., & Dai, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116222
Xu, Y., Lv, P., Zhang, Z., Li, L., Chai, Z., Li, Y., & Tang, C. (2026) · Forests · doi:10.3390/f17080983
Mate, A., Gupta, D., Radeva, P. I., & Bakde, A. M. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111263
Multi-Scale Residual Gated Attention U-Net for Liver Tumor Segmentation
Huang, H., Chen, Y., Peng, K., Guo, S., Deng, C., & Chen, H. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02291-6
Aby, A. E., Salaji, S., Anilkumar, K., & Rajan, T. (2026) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2026.2730508
Cao, A., Wang, X., Yang, R., Huang, T., Yao, R., Fan, C., Chen, W., Tan, Z., & Wang, Y. (2026) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2026.2723014
Atheeb, M. S., & Farhan, B. I. (2026) · Wasit Journal of Pure sciences · doi:10.31185/wjps.1001
Tran, H. N., Nguyen, C. T., Duong, T. T., Nguyen, M. L., & Nguyen, N. V. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-026-11720-1
Haridhas, A. K., & Alfred, L. F. (2026) · International Journal of Neuroscience · doi:10.1080/00207454.2026.2749809
Sun, B., Zhang, W., & Hu, X. (2026) · Scientific Reports · doi:10.1038/s41598-026-75069-z
Lightweight Deep Learning Model for Electrooculography-Based User Authentication
Li, Q., Cook, J., Tangban, A., Liao, W., & Yu, W. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-28466-2_8
Region Aware Squeeze-and-Excitation Networks for Image SegmentationPreprint
Roberts, J., Tummala, P., Sarna, K., & Neto, J. F. S. R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.15079
Mauri, L., Morresi, D., Anselmetto, N., Cavallo, S., Ferrero, S., Maroschek, M., Seidl, R., & Garbarino, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7620521
SVF-net: A Dual-encoder Network with Adaptive Gated Fusion for Colorectal Polyp Segmentation
Zhang, Z., Yu, L., & Tian, S. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02415-y
Toward Modality-Aware Preprocessing for Deep Learning-Based Blood Vessel Segmentation
Alkassar, S. H., & Sadeeq, H. T. (2026) · BioMedInformatics · doi:10.3390/biomedinformatics6050094
A Lightweight Skip-Connection Refinement for U-Net Lung Lesion Segmentation in CT Scans
Kishore, P., & D, N. D. (2026) · doi:10.1109/incect72370.2026.11742903
Transformer-Based U-Net with scSE Attention for Flood Segmentation in UAV Imagery
Fariza, F. N., Rohman, M. S., Winarsih, N. A. S., Ratmana, D. O., & Pramunendar, R. A. (2026) · International Seminar on Application for Technology of Information and Communication (iSemantic) · doi:10.1109/isemantic71495.2026.11742949
Roshan, S., Tanha, J., & Balafar, M. A. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135482
EMIPNet: An efficient feature-aware network for medical image segmentation and localization
Liu, H., Zhang, L., Ye, C., Liu, J., Yu, W., Zhang, Z., Lin, Z., Jiang, J., Zen, W., & 修忠标 (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111716
Progressive Learnable Counterfactual Attention for Music Classification
Lin, Y.-X., Wei, W.-L., Wang, J.-C., & Lin, J. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-147
Synthetic-Data-Augmented XCT Segmentation of Microscopic Damage in C/SiC Composites
Ma, L., Chen, Q., Xiao, C., Hu, Z., Yang, Z., & Chen, X. (2026) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2026.112288
Metadata
- Authors
- Roy, A. G., Navab, N., & Wachinger, C.
- Affiliations
- Technical University of Munich (DE)
- Ludwig-Maximilians-Universität München (DE)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2019-02
- Volume
- 38
- Issue
- 2
- Pages
- 540-549
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2888493720
- Cited by
- 534
- References
- 21
- Citations by year
- 2026: 64 · 2025: 66 · 2024: 90 · 2023: 78 · 2022: 94 · 2021: 85 · 2020: 37 · 2019: 19
- FWCI
- 17.76
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Bavarian State Ministry of Education, Science
- Arts in the Framework of the Centre Digitisation.Bavaria
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- squeeze-and-excitation module, semantic segmentation, fully convolutional network, channel recalibration, U-Net, network architecture design, medical image segmentation
- MeSH terms
- Brain, Diagnostic Imaging, Humans, Image Processing, Computer-Assisted, Retina, Databases, Factual, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.