{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T00:16:14Z","timestamp":1720224974086},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e0 degli Studi di Roma La Sapienza"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we design and evaluate the performance of the Multi-resolution Twinned Residual Auto-Encoders (MR-TRAE) model, a deep learning (DL)-based architecture specifically designed for achieving multi-resolution super-resolved images from low-resolution (LR) inputs at various scaling factors. For this purpose, we expand on the recently introduced Twinned Residual Auto-Encoders (TRAE) paradigm for single-image super-resolution (SISR) to extend it to the multi-resolution (MR) domain. The main contributions of this work include (i) the architecture of the MR-TRAE model, which utilizes cascaded trainable up-sampling modules for progressively increasing the spatial resolution of low-resolution (LR) input images at multiple scaling factors; (ii) a novel loss function designed for the joint and semi-blind training of all MR-TRAE model components; and (iii) a comprehensive analysis of the MR-TRAE trade-off between model complexity and performance. Furthermore, we thoroughly explore the connections between the MR-TRAE architecture and broader cognitive paradigms, including knowledge distillation, the teacher-student learning model, and hierarchical cognition. Performance evaluations of the MR-TRAE benchmarked against state-of-the-art models (such as U-Net, generative adversarial network (GAN)-based, and single-resolution baselines) were conducted using publicly available datasets. These datasets consist of LR computer tomography (CT) scans from patients with COVID-19. Our tests, which explored multi-resolutions at scaling factors <jats:inline-formula><jats:alternatives><jats:tex-math>$$\\times (2,4,8)$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mo>\u00d7<\/mml:mo>\n                    <mml:mo>(<\/mml:mo>\n                    <mml:mn>2<\/mml:mn>\n                    <mml:mo>,<\/mml:mo>\n                    <mml:mn>4<\/mml:mn>\n                    <mml:mo>,<\/mml:mo>\n                    <mml:mn>8<\/mml:mn>\n                    <mml:mo>)<\/mml:mo>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>, showed a significant finding: the MR-TRAE model can reduce training times by up to <jats:inline-formula><jats:alternatives><jats:tex-math>$$60\\%$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mn>60<\/mml:mn>\n                    <mml:mo>%<\/mml:mo>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> compared to those of the baselines, without a noticeable impact on achieved performance.<\/jats:p>","DOI":"10.1007\/s12559-024-10293-1","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T08:01:31Z","timestamp":1716278491000},"page":"1447-1469","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-resolution Twinned Residual Auto-Encoders (MR-TRAE)\u2014A Novel DL Model for Image Multi-resolution"],"prefix":"10.1007","volume":"16","author":[{"given":"Alireza","family":"Momenzadeh","sequence":"first","affiliation":[]},{"given":"Enzo","family":"Baccarelli","sequence":"additional","affiliation":[]},{"given":"Michele","family":"Scarpiniti","sequence":"additional","affiliation":[]},{"given":"Sima","family":"Sarv Ahrabi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,21]]},"reference":[{"key":"10293_CR1","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.inffus.2021.09.005","volume":"79","author":"H Chen","year":"2022","unstructured":"Chen H, He X, et al. Real-world single image super-resolution: a brief review. Inf Fusion. 2022;79:124\u201345. https:\/\/doi.org\/10.1016\/j.inffus.2021.09.005.","journal-title":"Inf Fusion"},{"key":"10293_CR2","doi-asserted-by":"publisher","unstructured":"Chauhan K, Patel SN, et al. Deep learning-based single-image super-resolution: a comprehensive review. IEEE Access. 2023;11:21811\u201330. https:\/\/doi.org\/10.1109\/ACCESS.2023.3251396.","DOI":"10.1109\/ACCESS.2023.3251396"},{"key":"10293_CR3","doi-asserted-by":"publisher","unstructured":"Villar-Corrales A, Schirrmacher F, Riess C. Deep learning architectural designs for super-resolution of noisy images. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). ICASSP\u201921. Toronto: IEEE; 2021. pp. 1635\u201339. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414733.","DOI":"10.1109\/ICASSP39728.2021.9414733"},{"key":"10293_CR4","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.inffus.2022.10.007","volume":"91","author":"DC Lepcha","year":"2023","unstructured":"Lepcha DC, Goyal B, et al. Image super-resolution: a comprehensive review, recent trends, challenges and applications. Inf Fusion. 2023;91:230\u201360. https:\/\/doi.org\/10.1016\/j.inffus.2022.10.007.","journal-title":"Inf Fusion"},{"issue":"8","key":"10293_CR5","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","volume":"16","author":"K Dabov","year":"2007","unstructured":"Dabov K, Foi A, et al. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process. 2007;16(8):2080\u201395. https:\/\/doi.org\/10.1109\/TIP.2007.901238.","journal-title":"IEEE Trans Image Process"},{"key":"10293_CR6","doi-asserted-by":"publisher","first-page":"118657","DOI":"10.1016\/j.eswa.2022.118657","volume":"212","author":"H Chen","year":"2023","unstructured":"Chen H, He X, et al. Self-supervised cycle-consistent learning for scale-arbitrary real-world single image super-resolution. Expert Syst Appl. 2023;212:118657. https:\/\/doi.org\/10.1016\/j.eswa.2022.118657.","journal-title":"Expert Syst Appl"},{"key":"10293_CR7","doi-asserted-by":"publisher","unstructured":"Wang Z, Chen J, Hoi SCH. Deep learning for image super-resolution: a survey. IEEE Trans Pattern Anal Mach Intell. 2021;43(10):3365\u201387. https:\/\/doi.org\/10.1109\/TPAMI.2020.2982166.","DOI":"10.1109\/TPAMI.2020.2982166"},{"issue":"3","key":"10293_CR8","doi-asserted-by":"publisher","first-page":"2850","DOI":"10.1007\/s11227-022-04775-y","volume":"79","author":"S Sarv Ahrabi","year":"2023","unstructured":"Sarv Ahrabi S, Momenzadeh A, Baccarelli E, Scarpiniti M, Piazzo L. How much BiGAN and CycleGAN-learned hidden features are effective for COVID-19 detection from CT images? A comparative study. J Supercomput. 2023;79(3):2850\u201381. https:\/\/doi.org\/10.1007\/s11227-022-04775-y.","journal-title":"J Supercomput"},{"key":"10293_CR9","doi-asserted-by":"publisher","unstructured":"Chou PA, Schaar M (Eds). Multimedia over IP and wireless networks: compression, networks: compression, networking, and systems, 1st edn. California: Academic Press; 2007. https:\/\/doi.org\/10.1016\/B978-0-12-088480-3.X5000-0","DOI":"10.1016\/B978-0-12-088480-3.X5000-0"},{"key":"10293_CR10","doi-asserted-by":"publisher","first-page":"103412","DOI":"10.1016\/j.bspc.2021.103412","volume":"73","author":"Y Chen","year":"2022","unstructured":"Chen Y, Zheng Q, Chen J. Double paths network with residual information distillation for improving lung CT image super resolution. Biomed Signal Process Control. 2022;73:103412. https:\/\/doi.org\/10.1016\/j.bspc.2021.103412.","journal-title":"Biomed Signal Process Control"},{"key":"10293_CR11","doi-asserted-by":"publisher","unstructured":"Li J, Fang F, et al. Multi-scale residual network for image super-resolution. In: 15th European Conference on Computer Vision (ECCV). ECCV\u201918. Munich; Springer: 2018. pp. 517\u201332. https:\/\/doi.org\/10.1007\/978-3-030-01237-3_32.","DOI":"10.1007\/978-3-030-01237-3_32"},{"issue":"5","key":"10293_CR12","doi-asserted-by":"publisher","first-page":"5461","DOI":"10.1109\/TPAMI.2022.3203009","volume":"45","author":"A Liu","year":"2023","unstructured":"Liu A, Liu Y, et al. Blind image super-resolution: a survey and beyond. IEEE Trans Pattern Anal Mach Intell. 2023;45(5):5461\u201380. https:\/\/doi.org\/10.1109\/TPAMI.2022.3203009.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10293_CR13","doi-asserted-by":"publisher","first-page":"120104","DOI":"10.1016\/j.eswa.2023.120104","volume":"225","author":"E Baccarelli","year":"2023","unstructured":"Baccarelli E, Scarpiniti M, Momenzadeh A. Twinned residual auto-encoder (TRAE)-A new DL architecture for denoising super-resolution and task-aware feature learning from COVID-19 CT images. Expert Syst Appl. 2023;225:120104. https:\/\/doi.org\/10.1016\/j.eswa.2023.120104.","journal-title":"Expert Syst Appl"},{"key":"10293_CR14","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted Intervention\u2013MICCAI 2015. MICCAI\u201915. Munich: Springer; 2015. pp. 234\u201341. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10293_CR15","doi-asserted-by":"publisher","unstructured":"Ledig C, Theis L, et al. Photo-realistic single image super-resolution using a generative adversarial network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017). Honolulu: IEEE; 2017. pp. 105\u201314. https:\/\/doi.org\/10.1109\/CVPR.2017.19.","DOI":"10.1109\/CVPR.2017.19"},{"key":"10293_CR16","doi-asserted-by":"publisher","first-page":"729287","DOI":"10.3389\/fmed.2021.729287","volume":"8","author":"H Gunraj","year":"2022","unstructured":"Gunraj H, Sabri A, et al. COVID-Net CT-2: enhanced deep neural networks for detection of COVID-19 from chest CT images through bigger, more diverse learning. Front Med. 2022;8:729287. https:\/\/doi.org\/10.3389\/fmed.2021.729287.","journal-title":"Front Med"},{"issue":"2","key":"10293_CR17","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2016","unstructured":"Dong C, Loy CC, et al. Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell. 2016;38(2):295\u2013307. https:\/\/doi.org\/10.1109\/TPAMI.2015.2439281.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10293_CR18","doi-asserted-by":"publisher","unstructured":"Lim B, Son S, et al. Enhanced deep residual networks for single image super-resolution. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). CVPRW\u201917. Honolulu: IEEE; 2017. pp. 1132\u201340. https:\/\/doi.org\/10.1109\/CVPRW.2017.151.","DOI":"10.1109\/CVPRW.2017.151"},{"key":"10293_CR19","doi-asserted-by":"publisher","unstructured":"Zhang Y, Tian Y, et al. Residual dense network for image super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201918. Salt Lake City: IEEE; 2018. pp. 2472\u201381. https:\/\/doi.org\/10.1109\/CVPR.2018.00262.","DOI":"10.1109\/CVPR.2018.00262"},{"key":"10293_CR20","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, et al. Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201917. Honolulu: IEEE; 2017. pp. 4700\u20138. https:\/\/doi.org\/10.1109\/CVPR.2017.243.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10293_CR21","doi-asserted-by":"publisher","unstructured":"Liu J, Zhang W, et al. Residual feature aggregation network for image super-resolution. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201920. Seattle: IEEE; 2020. pp. 2356\u201365. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00243.","DOI":"10.1109\/CVPR42600.2020.00243"},{"key":"10293_CR22","doi-asserted-by":"publisher","unstructured":"Lu L, Li W, et al. MASA-SR: matching acceleration and spatial adaptation for reference-based image super-resolution. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201921. Nashville: IEEE; 2021. pp. 6364\u201373. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00630.","DOI":"10.1109\/CVPR46437.2021.00630"},{"key":"10293_CR23","doi-asserted-by":"publisher","first-page":"2325","DOI":"10.1109\/TIP.2021.3050856","volume":"30","author":"Y Huang","year":"2021","unstructured":"Huang Y, Li J, et al. Interpretable detail-fidelity attention network for single image super-resolution. IEEE Trans Image Process. 2021;30:2325\u201339. https:\/\/doi.org\/10.1109\/TIP.2021.3050856.","journal-title":"IEEE Trans Image Process"},{"key":"10293_CR24","doi-asserted-by":"publisher","unstructured":"Wang L, Wang Y, et al. Unsupervised degradation representation learning for blind super-resolution. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201921. Nashville: IEEE; 2021. pp. 10576\u201385. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01044.","DOI":"10.1109\/CVPR46437.2021.01044"},{"key":"10293_CR25","doi-asserted-by":"publisher","unstructured":"Zhang Y, Li K, et al. Image super-resolution using very deep residual channel attention networks. In: European Conference on Computer Vision (ECCV). ECCV\u20192018. Munich: Springer; 2018. pp. 294\u2013310. https:\/\/doi.org\/10.1007\/978-3-030-01234-2_18.","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"10293_CR26","doi-asserted-by":"publisher","unstructured":"Dai T, Cai J, et al. Second-order attention network for single image super-resolution. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201919. Long Beach: IEEE; 2019. pp. 11057\u201366. https:\/\/doi.org\/10.1109\/CVPR.2019.01132.","DOI":"10.1109\/CVPR.2019.01132"},{"key":"10293_CR27","doi-asserted-by":"publisher","unstructured":"Niu B, et al. Single image super-resolution via a holistic attention network. In: Computer Vision\u2013ECCV 2020. ECCV\u201920. Glasgow: Springer; 2020. pp. 191\u2013207. https:\/\/doi.org\/10.1007\/978-3-030-58610-2_12.","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"10293_CR28","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1016\/j.neucom.2020.08.070","volume":"453","author":"Z Wang","year":"2021","unstructured":"Wang Z, Lu Y, et al. Single image super-resolution with attention-based densely connected module. Neurocomputing. 2021;453:876\u201384. https:\/\/doi.org\/10.1016\/j.neucom.2020.08.070.","journal-title":"Neurocomputing"},{"key":"10293_CR29","doi-asserted-by":"publisher","unstructured":"Liu H, Cao F, et al. Lightweight multi-scale residual networks with attention for image super-resolution. knowlBased Syst. 2020;203:106103. https:\/\/doi.org\/10.1016\/j.knosys.2020.106103.","DOI":"10.1016\/j.knosys.2020.106103"},{"key":"10293_CR30","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neunet.2020.08.008","volume":"132","author":"H Liu","year":"2020","unstructured":"Liu H, Cao F. Improved dual-scale residual network for image super-resolution. Neural Netw. 2020;132:84\u201395. https:\/\/doi.org\/10.1016\/j.neunet.2020.08.008.","journal-title":"Neural Netw"},{"key":"10293_CR31","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cag.2023.04.007","volume":"113","author":"X Song","year":"2023","unstructured":"Song X, Liu W, et al. Image super-resolution with multi-scale fractal residual attention network. Comput Graph. 2023;113:21\u201331. https:\/\/doi.org\/10.1016\/j.cag.2023.04.007.","journal-title":"Comput Graph"},{"key":"10293_CR32","doi-asserted-by":"publisher","first-page":"110718","DOI":"10.1016\/j.knosys.2023.110718","volume":"275","author":"Y Hu","year":"2023","unstructured":"Hu Y, Huang Y, Zhang K. Multi-scale information distillation network for efficient image super-resolution. knowlBased Syst. 2023;275:110718. https:\/\/doi.org\/10.1016\/j.knosys.2023.110718.","journal-title":"knowlBased Syst"},{"key":"10293_CR33","doi-asserted-by":"publisher","unstructured":"Ye S, Zhao S, et al. Single-image super-resolution challenges: a brief review. Electronics. 2023;12(13):2975. https:\/\/doi.org\/10.3390\/electronics12132975.","DOI":"10.3390\/electronics12132975"},{"key":"10293_CR34","doi-asserted-by":"publisher","unstructured":"Wang L, Dong X, et al. Exploring sparsity in image super-resolution for efficient inference. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). CVPR\u201921. Nashville: IEEE; 2021. pp. 4915\u201324. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00488.","DOI":"10.1109\/CVPR46437.2021.00488"},{"key":"10293_CR35","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TMM.2020.2999182","volume":"23","author":"C Tian","year":"2021","unstructured":"Tian C, Xu Y, et al. Coarse-to-fine CNN for image super-resolution. IEEE Trans Multimedia. 2021;23:1489\u2013502. https:\/\/doi.org\/10.1109\/TMM.2020.2999182.","journal-title":"IEEE Trans Multimedia"},{"issue":"6","key":"10293_CR36","doi-asserted-by":"publisher","first-page":"3718","DOI":"10.1109\/TSMC.2021.3069265","volume":"52","author":"C Tian","year":"2022","unstructured":"Tian C, Xu Y, et al. Asymmetric CNN for image superresolution. IEEE Trans Syst Man Cybern Syst. 2022;52(6):3718\u201330. https:\/\/doi.org\/10.1109\/TSMC.2021.3069265.","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10293_CR37","doi-asserted-by":"publisher","unstructured":"Lu Z, Li J, et al. Transformer for single image super-resolution. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). CVPRW\u201922. New Orleans: IEEE; 2022. pp. 456\u201365. https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00061.","DOI":"10.1109\/CVPRW56347.2022.00061"},{"key":"10293_CR38","doi-asserted-by":"publisher","first-page":"108373","DOI":"10.1016\/j.sigpro.2021.108373","volume":"192","author":"T-H Tran","year":"2022","unstructured":"Tran T-H, Berberich J, Simon S. 3DVSR: 3D EPI volume-based approach for angular and spatial light field image super-resolution. Signal Process. 2022;192:108373. https:\/\/doi.org\/10.1016\/j.sigpro.2021.108373.","journal-title":"Signal Process"},{"issue":"8","key":"10293_CR39","doi-asserted-by":"publisher","first-page":"4927","DOI":"10.1109\/TCSVT.2021.3138431","volume":"32","author":"Y Liu","year":"2022","unstructured":"Liu Y, Jia Q, et al. Cross-SRN: structure-preserving super-resolution network with cross convolution. IEEE Trans Circuits Syst Video Technol. 2022;32(8):4927\u201339. https:\/\/doi.org\/10.1109\/TCSVT.2021.3138431.","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10293_CR40","doi-asserted-by":"publisher","unstructured":"Aakerberg A, Johansen AS, et al. Semantic segmentation guided real-world super-resolution. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). WACVW\u201922. Waikoloa: IEEE; 2022. pp. 449\u201358. https:\/\/doi.org\/10.1109\/WACVW54805.2022.00051.","DOI":"10.1109\/WACVW54805.2022.00051"},{"key":"10293_CR41","doi-asserted-by":"publisher","unstructured":"Kong F, Li M, et al. Residual local feature network for efficient super-resolution. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). CVPRW\u201922. New Orleans: IEEE; 2022. pp. 765\u201375. https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00092.","DOI":"10.1109\/CVPRW56347.2022.00092"},{"key":"10293_CR42","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.neunet.2022.04.020","volume":"152","author":"A Yang","year":"2022","unstructured":"Yang A, Li L. Non-linear perceptual multi-scale network for single image super-resolution. Neural Netw. 2022;152:201\u201311. https:\/\/doi.org\/10.1016\/j.neunet.2022.04.020.","journal-title":"Neural Netw"},{"key":"10293_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10076-6","author":"KR Bhatele","year":"2022","unstructured":"Bhatele KR, Jha A, et al. COVID-19 detection: a systematic review of machine and deep learning-based approaches utilizing chest X-rays and CT scans. Cognit Comput. 2022. https:\/\/doi.org\/10.1007\/s12559-022-10076-6.","journal-title":"Cognit Comput"},{"key":"10293_CR44","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-020-09785-7","author":"T Goel","year":"2021","unstructured":"Goel T, Murugan R, et al. Automatic screening of COVID-19 using an optimized generative adversarial network. Cognit Comput. 2021. https:\/\/doi.org\/10.1007\/s12559-020-09785-7.","journal-title":"Cognit Comput"},{"issue":"7","key":"10293_CR45","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1109\/JAS.2021.1004009","volume":"8","author":"L Sun","year":"2021","unstructured":"Sun L, Liu Z, et al. Lightweight image super-resolution via weighted multi-scale residual network. IEEE\/CAA J Autom Sinica. 2021;8(7):1271\u201380. https:\/\/doi.org\/10.1109\/JAS.2021.1004009.","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"10293_CR46","doi-asserted-by":"publisher","unstructured":"Wang Y, Shao Z, et al. Remote sensing image super-resolution via multiscale enhancement network. IEEE Geosci Remote Sens Lett. 2023;20:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2023.3248069.","DOI":"10.1109\/LGRS.2023.3248069"},{"key":"10293_CR47","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning, 1st edn. Cambridge: The MIT Press; 2016. https:\/\/mitpress.mit.edu\/9780262035613\/deep-learning\/."},{"key":"10293_CR48","doi-asserted-by":"publisher","unstructured":"Li W, Du Z, et al. Hierarchical feature aggregation network for deep image compression. In: 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). ICASSP\u201922. Singapore: IEEE; 2022. pp. 1875\u20139. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746628.","DOI":"10.1109\/ICASSP43922.2022.9746628"},{"issue":"1","key":"10293_CR49","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.1080\/09540091.2022.2082384","volume":"34","author":"D Yang","year":"2022","unstructured":"Yang D, Du Y, et al. Image semantic segmentation with hierarchical feature fusion based on deep neural network. Connect Sci. 2022;34(1):1772\u201384. https:\/\/doi.org\/10.1080\/09540091.2022.2082384.","journal-title":"Connect Sci"},{"key":"10293_CR50","doi-asserted-by":"publisher","unstructured":"Scardapane S, Scarpiniti M, et al. Why should we add early exits to neural networks? Cognit Comput. 2020. https:\/\/doi.org\/10.1007\/s12559-020-09734-4.","DOI":"10.1007\/s12559-020-09734-4"},{"key":"10293_CR51","doi-asserted-by":"publisher","unstructured":"Chen W, Ma Y, et al. Hierarchical generative adversarial networks for single image super-resolution. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). WACV\u201921. Waikoloa: IEEE; 2021. pp. 355\u201364. https:\/\/doi.org\/10.1109\/WACV48630.2021.00040.","DOI":"10.1109\/WACV48630.2021.00040"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-024-10293-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-024-10293-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-024-10293-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T09:47:02Z","timestamp":1720172822000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-024-10293-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,21]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10293"],"URL":"https:\/\/doi.org\/10.1007\/s12559-024-10293-1","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,21]]},"assertion":[{"value":"23 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}