CAAT: Image super-resolution algorithm via channel attention and transformer
Open accessAbstract
Deep learning-based single image super-resolution (SISR) has achieved remarkable progress, yet the trade-off between reconstruction quality and computational efficiency remains a critical challenge for real-time applications. This paper proposes a novel Channel Attention and Transformer framework (CAAT) that synergistically integrates convolutional operations with Swin Transformer blocks to achieve lightweight yet high-performance SR. The core innovation lies in the Channel-Attention-Embedded Transformer Block, which adaptively injects channel attention mechanisms into both Transformer self-attention and convolutional feature streams, enabling discriminative feature selection and cross-modal fusion at the block level. By alternately stacking convolution and Transformer layers with channel-wise adaptive weighting, proposed leverages their complementary strengths in local detail preservation and global context modeling while maintaining model compactness. Extensive evaluations on five benchmark datasets across three scales demonstrate that proposed achieves superior performance over six state-of-the-art methods. Notably, at × 4 magnification, proposed attains 0.09 dB PSNR improvement on Urban100 and 0.30 dB on Manga109 compared to the best counterparts, while reducing parameters by 51 % versus SwinIR and FLOPs by 68 % (195.6G vs. 612.6G for 1280 × 720 input). These results, substantiated by statistical significance tests and ablation studies, confirm proposed efficacy as a cost…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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 · see citing works
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216 · see citing works
Enhanced Deep Residual Networks for Single Image Super-Resolution
Lim, B. O., Son, S., Kim, H., Nah, S., & Lee, K. M. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.151 · Cited by 8,117 · see citing works
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870 · see citing works
Image Super-Resolution Using Very Deep Residual Channel Attention NetworksPreprint
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018) · European Conference on Computer Vision · doi:10.48550/arxiv.1807.02758 · Cited by 5,655 · see citing works
NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study
Agustsson, E., & Timofte, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.150 · Cited by 4,295 · see citing works
Single image super-resolution from transformed self-exemplars
Huang, J., Singh, A., & Ahuja, N. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7299156 · Cited by 3,603 · see citing works
On Single Image Scale-Up Using Sparse-Representations
Zeyde, R., Elad, M., & Protter, M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-27413-8_47 · Cited by 3,371 · see citing works
Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding
Bevilacqua, M., Roumy, A., Guillemot, C. M., & Morel, M.-L. A. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.135 · Cited by 3,162 · see citing works
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
Lai, W., Huang, J., Ahuja, N., & Yang, M. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.618 · Cited by 3,111 · see citing works
Pre-Trained Image Processing Transformer
Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., & Gao, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01212 · Cited by 2,308 · see citing works
Deep Back-Projection Networks for Super-ResolutionPreprint
Haris, M., Shakhnarovich, G., & Ukita, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.48550/arxiv.1803.02735 · Cited by 1,518 · see citing works
Fast, Accurate, and, Lightweight Super-Resolution with Cascading Residual Network
Ahn, N., Kang, B., & Sohn, K. (2018) · European Conference on Computer Vision · doi:10.48550/arxiv.1803.08664 · Cited by 1,477
NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results
Timofte, R., Agustsson, E., Gool, L. V., Yan, S., Lei Zhang, A., Lim, B. O., Son, S., Kim, H., Nah, S., Lee, K. M., et al. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.149 · Cited by 1,465 · see citing works
Self-citationSketch-based manga retrieval using manga109 dataset
Matsui, Y., Ito, K., Aramaki, Y., Fujimoto, A., Ogawa, T., Yamasaki, T., & Aizawa, K. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4020-z · Cited by 1,454 · see citing works
Image Super-Resolution with Non-Local Sparse Attention
Mei, Y., Fan, Y., & Zhou, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00352 · Cited by 657 · see citing works
Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars MiningPreprint
Mei, Y.-Q., Fan, Y.-C., Zhou, Y.-Q., Huang, L.-C., Huang, T. S., & Shi, H. (2020) · Computer Vision and Pattern Recognition · doi:10.48550/arxiv.2006.01424 · Cited by 371 · see citing works
Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices
Zhang, X., Zeng, H., & Lei Zhang, A. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475291 · Cited by 243 · see citing works
A Review of Key Technologies for Emotion Analysis Using Multimodal Information
Zhu, X., Guo, C., Feng, H., Huang, Y., Feng, Y., Wang, X., & Wang, R. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10287-z · Cited by 137 · see citing works
Zhu, X., Wang, Y., Cambria, E., Rida, I., López, J. S., Cui, L., & Wang, R. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103268 · Cited by 130 · see citing works
RAFT: Robust Adversarial Fusion Transformer for multimodal sentiment analysis
Wang, R., Xu, D., Cascone, L., Wang, Y.-Y., Chen, H., Zheng, J., & Zhu, X.-X. (2025) · Array · doi:10.1016/j.array.2025.100445 · Cited by 128 · see citing works
Zhu, X.-X., Liu, Z., Cambria, E., Yu, X.-H., Fan, X., Chen, H., & Wang, R. (2024) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2024.108564 · Cited by 128 · see citing works
CIME: Contextual Interaction-Based Multimodal Emotion Analysis With Enhanced Semantic Information
Wang, R., Guo, C., Shabaz, M., Rida, I., Cambria, E., & Zhu, X. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3572495 · Cited by 79 · see citing works
A Generative Random Modality Dropout Framework for Robust Multimodal Emotion Recognition
Zhang, Y., Chen, H., Rida, I., Zhu, X.-X., & Cambria, E. (2025) · IEEE Intelligent Systems · doi:10.1109/mis.2025.3597120 · Cited by 76
Edge-enhanced Feature Distillation Network for Efficient Super-Resolution
Wang, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00093 · Cited by 76 · see citing works
Contrastive-Based Removal of Negative Information in Multimodal Emotion Analysis
Wang, R., Wang, Y.-Y., Cambria, E., Fan, X.-H., Yu, X.-H., Huang, Y., Xiaosong, E., & Zhu, X.-X. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10463-9 · Cited by 70 · see citing works
EMVAS: end-to-end multimodal emotion visualization analysis system
Zhu, X., Feng, H., Cambria, E., Huang, Y., Ju, M., Yuan, H., & Wang, R. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01931-8 · Cited by 34 · see citing works
Generalizable deepfake detection via Spatial Kernel Selection and Halo Attention Network
Guo, S., Li, Q., Gao, M., Zhu, X., & Rida, I. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105582 · Cited by 30 · see citing works
Deepfake detection via Feature Refinement and Enhancement Network
Song, W., Guo, S., Gao, M.-L., Li, Q.-L., Zhu, X., & Rida, I. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105663 · Cited by 26 · see citing works
Ye, Y.-X., Liu, N., Zhao, Y., Zhu, X., Wang, J., & Liu, Y. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111993 · Cited by 23
Chen, J., Xing, D., Shabaz, M., Zhu, Y., Wang, Y., & Zhu, X. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105721 · Cited by 21 · see citing works
Zhang, J.-M., Jiang, J., Feng, Z., & Wang, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114567 · Cited by 12 · see citing works
Khan, R., Alzaben, N., Daradkeh, Y., Zhu, X., & Ullah, I. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105670 · Cited by 11
Learning disturbance-aware correlation filter with adaptive Kaiser window for visual object tracking
Zhang, J.-M., Dai, J., Chen, W., & Ke, N. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105585 · Cited by 5 · see citing works
Topology-aware dual-branch network via lightweight Mamba for crack segmentation and quantification
Zhang, J.-M., Li, D.-W., Zhang, S., Zhang, R., & Zhang, J. (2025) · Measurement · doi:10.1016/j.measurement.2025.119180 · Cited by 4 · see citing works
A Dual-branch Progressive Network with spatial-frequency constraint for image fusion
Wang, Z., Song, W., Xing, X., Liu, L., Zhu, X., & Gao, M.-L. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105709 · Cited by 4
CEDT2M: text-driven human motion generation via cross-modal mixture of encoder-decoder
Wang, X., Li, P., & Wang, R. (2025) · Neural computing & applications (Print) · doi:10.1007/s00521-025-11112-w · Cited by 2 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
DPC-DCD: A density peak clustering algorithm based on density conflict domains
Tu, H., Li, C., Hou, H.-W., & Ding, S.-F. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115676 · Cited by 6
Pseudo-depth-based deep neural network model for object detection
Li, S.-Q., Feng, W., Liu, B., Tong, X., & Li, Q. (2026) · Scientific Reports · doi:10.1038/s41598-026-45310-w · Cited by 3 · see citing works
Kui, X.-Y., Hu, Z.-P., Ji, Z.-X., Jiang, S., Xiao, Q.-M., Zou, Z.-W., Li, Q.-S., Li, Y., Zou, B.-J., & Chen, L.-M. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133326 · Cited by 3 · see citing works
Self-citationLeveraging ISTA-inspired Transformer and multi-scale CNN for image compressive sensing
Xie, Z.-H., Fan, Z.-C., Tang, H., Liu, L.-J., & Jiang, H. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104809 · Cited by 2 · see citing works
High-precision automated grading of flue-cured tobacco leaves based on hierarchical feature fusion
Pang, S.-P., Xin, X.-W., Ge, W., Zhang, Y., & Jia, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-45252-3 · Cited by 2 · see citing works
“With the advancement of Transformer-based models 23 , the accuracy of tobacco leaf grading has been further improved.”
MATdiff: Mask-aware transformer with diffusion model for large-mask image inpainting
Wang, S.-X., Zhao, W.-J., Liang, J., Zhang, W.-M., & Zhao, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133042 · Cited by 2 · see citing works
Sharma, A., Sharma, C., Prashar, D., Tiwari, P., Khan, A., Ayub, M. S., & Koo, I. (2026) · Scientific Reports · doi:10.1038/s41598-026-61702-4 · Cited by 1
“Equally, Transformer models of image enhancement tasks that focus on attention underscore the significance of local and global features fusion 39,40 .”
Universum graph-embedded kernel-based weighted extreme learning machine for handling class imbalance
Raghuwanshi, B. S. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2026.131243 · Cited by 1 · see citing works
Temporally consistent low-light face video enhancement via video-to-video conditional diffusion
Ding, X., He, K., Sun, H., & Yang, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-44219-8
“In the context of spatial detail recovery, channel attention mechanisms combined with Transformer architectures 27 have shown promise for lightweight yet effective feature extraction, which is particularly relevant for preserving fine-grained facial details in low-light scenarios.”
Luo, X.-T., Wang, Y., & Ren, Y. (2026) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2026.116138
Hierarchical feature attention network for image super-resolution
Li, D., Yang, S.-L., Liu, Z.-H., & Zhang, H. (2026) · Cluster Computing · doi:10.1007/s10586-026-06707-4
“To further enhance the contribution of channel information in Transformers, CAAT [32] embedded a channel attention mechanism inside the Transformer block, thereby achieving block-level feature selection and cross-modal fusion.”
SwinMED: Edge-texture enhanced SwinIR for medical image super-resolution
Aymaz, S., & Aymaz, Ş. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116665
Recent innovation in vision-based human activity recognition: a systematic survey
Yadav, D., Rani, D., Verma, O. P., & Sharma, T. K. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.105004
Mamba-enhanced low-resolution prior guided Chinese painting image inpainting
Peng, X.-L., Hu, Q.-Y., Zhang, Z.-Y., Qu, S.-Y., Chen, N.-N., & Gabbouj, M. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116397
Attribute-controlled diffusion model for diverse image inpainting
Han, N., Geng, G.-H., Deng, J.-H., & Li, Z. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116396
Zandi, G., & Ashouri-Talouki, M. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135135
FoTa-Net: Boundary-conditioned spatial–spectral coordination for large mask image inpainting
Peng, H., Wang, K.-H., Zheng, W.-F., Lan, G.-S., & Yu, Y. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116520
Sun, Z.-P., Guo, L., Mu, J., Qu, T., & Pan, Y. (2026) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2026.114810
A motion-based framework for real-time anomaly detection in crowded scenes
Mabrouk, D., Abdel-Fattah, M. A., & Taha, A. (2026) · Neural computing & applications (Print) · doi:10.1007/s00521-026-12260-3
“The problem stems from the inherent difficulty of segmenting cracks due to complex backgrounds, noise, and the elongated, irregular shapes of fractures, which traditional CNNs struggle to capture globally [20 ].”
Sha, H., & Han, Z. (2026) · Computational Geosciences · doi:10.1016/j.cageo.2026.106158
Synthetic Image Detection Based on Multi-Level Feature Fusion and Data Augmentation
Lin, G.-H., Lin, Y.-T., & Chen, J.-L. (2026) · ICT express · doi:10.1016/j.icte.2026.05.018
Dual-branch soft-activation switch distillation network for efficient image super-resolution
Tang, Y., Cai, X.-M., & Chen, J. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115807
Xu, X.-Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-54621-x
“For image super-resolution, Chen et al. 37 introduced CAT (Channel Attention and Transformer), which synergistically integrates convolutional operations with Swin Transformer blocks through channel-attention-embedded mechanisms, achieving superior reconstruction quality while reducing computational…”
InfluentialYang, R., Sun, Q., Cao, H., Lin, K., & Shen, C. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132870
Enhancing seismic inversion fidelity via adaptive multi-frequency and multi-scale fusion
Wang, Y.-M., Xu, Q., Pan, S.-L., Peng, B., & Min, F. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115562
Liu, F., Zhou, X., & Wang, J. (2026) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2026.109381
Su, B.-W., Chen, X.-P., Dai, Y.-H., Guan, T., & Li, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133757
AMETracker: transformer tracking with asymmetric mix encoder
Chen, W., Zhang, J., & Yu, L. (2026) · Signal, Image and Video Processing · doi:10.1007/s11760-026-05273-x
MBP: Rethinking class-imbalanced semi-supervised learning from the multi-binary perspective
Ye, C.-T., Meng, Q., & Ouyang, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133273
SPIR: Reinforcement learning based semantic guided adaptive degraded image restoration
Ding, Q., Wang, J., & Xian, Y. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2026.132082
SAT: shift alignment transformer for video denoising without flow estimation
Zhang, X., Fan, S.-Y., Zhang, H., Gao, Y., & Hu, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-38431-9
Sun, M.-J., & Sun, L. (2026) · Connection science · doi:10.1080/09540091.2026.2622889
Guo, Y.-F., Wang, Y.-C., Zhang, Z.-H., Ma, F., Meng, J., & Li, D.-P. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111250
- Authors
- Chen, Y., Chen, L., Xia, R., Yang, K., & Zou, K.
- Affiliations
- China Agricultural University (CN)
- Department of Science and Technology of Hunan Province (CN)
- Zoomlion (China) (CN)
- Corresponding author
- Chen, Yuantao
- Venue
- Array
- Publisher
- Elsevier BV
- Published
- 2025-12
- Volume
- 28
- Pages
- 100628
- ISSN
- 2590-0056 (ISSN-L)
- OpenAlex
- W4416940114
- Cited by
- 29
- References
- 36
- Citations by year
- 2026: 29
- FWCI
- 10.25
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Array (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Science and Technology Innovative Research Team in Higher Educational Institutions of Hunan Province
- Changsha Science and Technology Bureau (KQ2402169)
- Natural Science Foundation of Hunan Province
- Scientific Research Foundation of Hunan Provincial Education Department (HNJG-20231521)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- single image super-resolution, channel attention, Swin Transformer, lightweight neural networks, real-time image enhancement, cross-modal feature fusion, model compression, computational efficiency
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
