EVOLUSI PENDEKATAN DEEP LEARNING BERBASIS ATTENTION MECHANISM PADA PENINGKATAN RESOLUSI CITRA: TINJAUAN KOMPREHENSIF
Abstract
This study presents a Systematic Literature Review (SLR) on the development of attention-based deep learning methods for Single Image Super-Resolution (SISR) for the period 2022–2026. Using the PRISMA 2020 framework, 53 articles were selected from 1,116 identified articles from Scopus, IEEE Xplore, ScienceDirect, and SpringerLink. The study results show that hybrid CNN-Transformer architectures with attention mechanisms dominate the current trend, with channel attention being the most widely used (71.7%). Application domains include medical imaging, remote sensing, surveillance, multimedia, and industry. Key challenges identified include model complexity, limited generalization, and the trade-off between reconstruction quality and inference efficiency. This study provides a comprehensive roadmap for developing more adaptive and efficient attention-based SISR systems.
Penelitian ini menyajikan Systematic Literature Review (SLR) terhadap perkembangan metode deep learning berbasis attention mechanism untuk Single Image Super-Resolution (SISR) pada periode 2022–2026. Menggunakan kerangka PRISMA 2020, sebanyak 53 artikel dipilih dari 1.116 artikel teridentifikasi dari Scopus, IEEE Xplore, ScienceDirect, dan SpringerLink. Hasil kajian menunjukkan bahwa arsitektur hibrida CNN-Transformer dengan attention mechanism mendominasi tren terkini, dengan channel attention sebagai jenis yang paling banyak digunakan (71,7%). Domain aplikasi mencakup pencitraan medis, pengindraan jauh, surveillance, multimedia, dan industri. Tantangan utama yang teridentifikasi meliputi kompleksitas model, keterbatasan generalisasi, dan trade-off antara kualitas rekonstruksi dan efisiensi inferensi. Penelitian ini memberikan peta jalan komprehensif bagi pengembangan sistem SISR berbasis attention yang lebih adaptif dan efisien.
Full Text:
PDFReferences
Anwar, S., Barnes, N., & Petersson, L. (2025). Attention-based real image restoration. IEEE Transactions on Neural Networks and Learning Systems, 36(3), 3954–3964. https://doi.org/10.1109/TNNLS.2021.3131739
Ariav, I., & Cohen, I. (2023). Fully cross-attention transformer for guided depth super-resolution. Sensors, 23(5), Article 2723. https://doi.org/10.3390/s23052723
Chauhan, K., et al. (2023). Deep learning-based single-image super-resolution: A comprehensive review. IEEE Access, 11, 21811–21830. https://doi.org/10.1109/ACCESS.2023.3251396
Chen, J., Wang, W., Xing, F., & Tu, H. (2023). Multi-feature fusion attention network for single image super-resolution. IET Image Processing, 17(5), 1389–1402. https://doi.org/10.1049/ipr2.12721
Chen, Y., Chen, L., Xia, R., Yang, K., & Zou, K. (2025). CAAT: Image super-resolution algorithm via channel attention and transformer. Array, 28, Article 100628. https://doi.org/10.1016/j.array.2025.100628
Cheng, R., Wu, Y., Wang, J., Ma, M., Niu, Y., & Shi, G. (2022). Adaptive feature denoising based deep convolutional network for single image super-resolution. Computer Vision and Image Understanding, 223, Article 103518. https://doi.org/10.1016/j.cviu.2022.103518
Cho, G., & Choi, Y. S. (2024). Image super-resolution with unified-window attention. IEEE Access, 12, 30852–30866. https://doi.org/10.1109/ACCESS.2024.3368436
Ghazali, A. B. E., Fiaz, A., & Islam, M. (2025). Lightweight multi-stage holistic attention-based network for image super-resolution. IET Image Processing, 19(1), Article e70013. https://doi.org/10.1049/ipr2.70013
Gong, J., & Xu, Q. (2025). Temporal transformer-based video super-resolution reconstruction with cross-modal attention. Informatica, 49(10), 179–190. https://doi.org/10.31449/inf.v49i10.7146
Gurrola-Ramos, J., Alarcon, T. E., & Dalmau, O. (2022). Arbitrary scale super-resolution neural network based on residual channel-spatial attention. IEEE Access, 10, 108697–108709. https://doi.org/10.1109/ACCESS.2022.3211302
Haddaway, N. R., Page, M. J., Pritchard, C. C., & McGuinness, L. A. (2022). PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and open synthesis. Campbell Systematic Reviews, 18, Article e1230.
Hajian, A., & Aramvith, S. (2025). AERU-Net: Adaptive edge recovery and attention U-shaped network for remote sensing image super-resolution. IEEE Access, 13, 59177–59197. https://doi.org/10.1109/ACCESS.2025.3556312
Han, X., Wang, L., Wang, X., Zhang, P., & Xu, H. (2023). A multi-scale recursive attention feature fusion network for image super-resolution reconstruction algorithm. Sensors, 23(23), Article 9458. https://doi.org/10.3390/s23239458
Hassan, M., Illanko, K., & Fernando, X. N. (2024). Single image super resolution using deep residual learning. AI, 5(1), 426–445. https://doi.org/10.3390/ai5010021
Jia, F., Tan, L., Wang, G., Jia, C., & Chen, Z. (2023). A super-resolution network using channel attention retention for pathology images. PeerJ Computer Science, 9, Article e1196. https://doi.org/10.7717/peerj-cs.1196
Jiang, J., et al. (2022). Super-resolution reconstruction of 3T-like images from 0.35T MRI using a hybrid attention residual network. IEEE Access, 10, 32810–32821. https://doi.org/10.1109/ACCESS.2022.3155226
Kirat, O., & Yerlikaya, T. (2025). Edge-aware reparameterizable network with hybrid bottlenecks and spatial attention for efficient compressed image super-resolution. IEEE Access, 13, 206256–206271. https://doi.org/10.1109/ACCESS.2025.3640518
Kou, Q., et al. (2023). Single image super resolution via multi-attention fusion recurrent network. IEEE Access, 11, 98653–98665. https://doi.org/10.1109/ACCESS.2023.3314196
Lee, D. Y., Kim, J. Y., & Cho, S. Y. (2025). Improving medical image quality using a super-resolution technique with attention mechanism. Applied Sciences, 15(2), Article 867. https://doi.org/10.3390/app15020867
Li, H.-A., Wang, D., Zhang, J., Li, Z., & Ma, T. (2023). Image super-resolution reconstruction based on multiscale dual-attention. Connection Science, 35(1). https://doi.org/10.1080/09540091.2023.2182487
Li, X., Sun, H., & Li, T.-Q. (2026). CHARMS: A CNN-transformer hybrid with attention regularization for MRI super-resolution. Sensors, 26(2), Article 738. https://doi.org/10.3390/s26020738
Li, Y., & Li, W. (2026). A multi-scale hybrid attention residual network for super-resolution image reconstruction. IEEE Access, 14, 33847–33857. https://doi.org/10.1109/ACCESS.2026.3667149
Li, Z.-L., et al. (2025). DRFAN: A lightweight hybrid attention network for high-fidelity image super-resolution in visual inspection applications. Algorithms, 18(8), Article 454. https://doi.org/10.3390/a18080454
Liu, G., Zhou, S., Chen, X., Yue, W., & Ke, J. (2024). Recurrent large kernel attention network for efficient single infrared image super-resolution. IEEE Access, 12, 923–935. https://doi.org/10.1109/ACCESS.2023.3344830
Liu, J., & Chandrasiri, N. P. (2024). CA-ESRGAN: Super-resolution image synthesis using channel attention-based ESRGAN. IEEE Access, 12, 25740–25748. https://doi.org/10.1109/ACCESS.2024.3363172
Liu, J., et al. (2026). BAID: A lightweight super-resolution network with binary attention-guided frequency-aware information distillation. Computers, Materials & Continua, 86(2). https://doi.org/10.32604/cmc.2025.071397
Liu, S., Weng, X., Gao, X., Xu, X., & Zhou, L. (2024). A residual dense attention generative adversarial network for microscopic image super-resolution. Sensors, 24(11), Article 3560. https://doi.org/10.3390/s24113560
Liu, X., Gu, Z., Ding, H., Zhang, M., & Wang, L. (2024). Underwater image super-resolution using frequency-domain enhanced attention network. IEEE Access, 12, 6136–6147. https://doi.org/10.1109/ACCESS.2024.3351730
Lu, Z., Tu, Z., Zhang, Z., Jiang, C., & Chen, P. (2025). Single image super-resolution reconstruction based on multilayer residual networks with attention mechanisms. IEEE Access, 13, 73794–73802. https://doi.org/10.1109/ACCESS.2025.3562843
Ma, C., Mi, J., Gao, W., & Tao, S. (2024). Pyramid separable channel attention network for single image super-resolution. Computers, Materials & Continua, 80(3), 4687–4701. https://doi.org/10.32604/cmc.2024.055803
Muhammad, W., Aramvith, S., & Onoye, T. (2024). CANS: Combined attention network for single image super-resolution. IEEE Access, 12, 167498–167517. https://doi.org/10.1109/ACCESS.2024.3487918
Nasir, M. F., Rehman, M. U., & Hussain, I. (2025). A self-attention guided approach for advanced underwater image super-resolution with depth awareness. IEEE Open Journal of the Computer Society, 6, 1716–1726. https://doi.org/10.1109/OJCS.2025.3623788
Ning, Y., et al. (2025). A multi-head attention-based lightweight generative adversarial network for thyroid ultrasound video super-resolution. IEEE Access, 13, 99628–99640. https://doi.org/10.1109/ACCESS.2025.3570905
Patnaik, A., Chaudhary, N., Bhuyan, M. K., Alfarhood, S., & Safran, M. (2024). Remote sensing single-image super-resolution using convolutional block attention residual network with joint adversarial mechanisms. IEEE Access, 12, 53424–53435. https://doi.org/10.1109/ACCESS.2024.3387981
Qiao, F., Zhu, Y., Li, G., & Li, B. (2024). Dual contrastive attention-guided deformable convolutional network for single image superresolution. Journal of Visual Communication and Image Representation, 100, Article 104097. https://doi.org/10.1016/j.jvcir.2024.104097
Song, J., Sowmya, A., Zhang, W., & Sun, C. (2025). Efficient transformer with compressed-attention for stereo image super-resolution. Knowledge-Based Systems, 331, Article 114844. https://doi.org/10.1016/j.knosys.2025.114844
Sultan, N., Ruangsang, W., & Aramvith, S. (2025). HybridATNet: Multi-scale attention and hybrid feature refinement network for remote sensing image super-resolution. IEEE Access, 13, 159979–159997. https://doi.org/10.1109/ACCESS.2025.3608009
Talreja, J., Aramvith, S., & Onoye, T. (2023). DANS: Deep attention network for single image super-resolution. IEEE Access, 11, 84379–84397. https://doi.org/10.1109/ACCESS.2023.3302692
Tang, M., Gan, Y., Zhang, Y., & Gan, X. (2025). A lightweight super-resolution network for infrared images based on an adaptive attention mechanism. Computers, Materials & Continua, 84(2), 2699–2716. https://doi.org/10.32604/cmc.2025.064541
Tarasiewicz, T., & Kawulok, M. (2025). A graph attention network for real-world multi-image super-resolution. Information Fusion, 124, Article 103325. https://doi.org/10.1016/j.inffus.2025.103325
Wan, X., Xu, S., & Gao, G. (2025). Attention-assisted dual-branch interactive face super-resolution network. Cognitive Robotics, 5, 77–85. https://doi.org/10.1016/j.cogr.2025.01.001
Wang, P., Wu, Z., Ding, Z., & Zheng, B. (2024). BTAN: Lightweight superresolution network with target transform and attention. Computing and Informatics, 43(2), 414–437. https://doi.org/10.31577/cai_2024_2_414
Xu, Y., Guo, T., & Wang, C. (2024). A remote sensing image super-resolution reconstruction model combining multiple attention mechanisms. Sensors, 24(14), Article 4492. https://doi.org/10.3390/s24144492
Yan, T., & Yin, H. (2024). High-frequency channel attention and contrastive learning for image super-resolution. The Visual Computer, 40(12), 8839–8851. https://doi.org/10.1007/s00371-024-03276-8
Yu, C., & Pei, H. (2025). Super-resolution reconstruction method of face image based on attention mechanism. IEEE Access, 13, 121250–121260. https://doi.org/10.1109/ACCESS.2021.3070898
Yu, J., Lin, C., Peng, L., Zhong, C., & Li, H. (2025). MSFANet: A multi-scale feature fusion transformer with hybrid attention for remote sensing image super-resolution. Sensors, 25(21), Article 6729. https://doi.org/10.3390/s25216729
Yu, W., et al. (2022). Super-resolution reconstruction of speckle images of engineered bamboo based on an attention-dense residual network. Sensors, 22(17), Article 6693. https://doi.org/10.3390/s22176693
Zahan, N., Paheding, S., Saleem, A., Havens, T. C., & Esselman, P. C. (2025). MIMAR-Net: Multiscale inception-based Manhattan attention residual network and its application to underwater image super-resolution. Electronics, 14(22), Article 4544. https://doi.org/10.3390/electronics14224544
Zhang, J., Wang, Y., Dai, R., Zhan, T., & Yu, X. (2025). Spatial–spectral cross fusion attention based hyperspectral image super-resolution for land resource auditing. Informatica, 49(22), 93–110. https://doi.org/10.31449/inf.v49i22.7634
Zhang, S., Tong, S., & Pang, K. (2025). EECD-Net: An energy-efficient crack detection framework integrating super-resolution, spiking neural networks, and gated attention. IEEE Access, 13, 217349–217363. https://doi.org/10.1109/ACCESS.2025.3647946
Zhang, X., et al. (2024). Improving single-image super-resolution with dilated attention. Electronics, 13(12), Article 2281. https://doi.org/10.3390/electronics13122281
Zhang, Y., Gan, Y., Tang, M., & Gan, X. (2026). A super-resolution generative adversarial network for remote sensing images based on improved residual module and attention mechanism. Computers, Materials & Continua, 86(2). https://doi.org/10.32604/cmc.2025.068880
Zhang, Z., Su, Z., Song, W., & Ning, K. (2022). Global attention super-resolution algorithm for nature image edge enhancement. Sustainability, 14(21), Article 13865. https://doi.org/10.3390/su142113865
Zou, S., Ruan, M., Zhu, X., & Nie, W. (2023). Super-resolution reconstruction based on Gaussian transform and attention mechanism. PeerJ Computer Science, 9, Article e1182. https://doi.org/10.7717/peerj-cs.1182
DOI: https://doi.org/10.56486/jris.vol6no2.1342
Article Metrics
Abstract view : 0 timesPDF - 0 times
Refbacks
- There are currently no refbacks.
TERINDEKS OLEH :





