{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:08:14Z","timestamp":1761646094916,"version":"build-2065373602"},"reference-count":47,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T00:00:00Z","timestamp":1602633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806173"],"award-info":[{"award-number":["61806173"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2019J01855, 2019J01854"],"award-info":[{"award-number":["2019J01855, 2019J01854"]}]},{"name":"the Scientific Research Foundation of Xiamen for the Returned Overseas Chinese Scholars","award":["XRS[2018] No.310"],"award-info":[{"award-number":["XRS[2018] No.310"]}]},{"name":"Scientific Research Fund of Fujian Provincial Education Department, China","award":["JT180440"],"award-info":[{"award-number":["JT180440"]}]},{"name":"the Science and Technology Program of Xiamen China","award":["3502Z20179032"],"award-info":[{"award-number":["3502Z20179032"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Recent years have witnessed the great success of image super-resolution based on deep learning. However, it is hard to adapt a well-trained deep model for a specific image for further improvement. Since the internal repetition of patterns is widely observed in visual entities, internal self-similarity is expected to help improve image super-resolution. In this paper, we focus on exploiting a complementary relation between external and internal example-based super-resolution methods. Specifically, we first develop a basic network learning external prior from large scale training data and then learn the internal prior from the given low-resolution image for task adaptation. By simply embedding a few additional layers into a pre-trained deep neural network, the image-adaptive super-resolution method exploits the internal prior for a specific image, and the external prior from a well-trained super-resolution model. We achieve 0.18 dB PSNR improvements over the basic network\u2019s results on standard datasets. Extensive experiments under image super-resolution tasks demonstrate that the proposed method is flexible and can be integrated with lightweight networks. The proposed method boosts the performance for images with repetitive structures, and it improves the accuracy of the reconstructed image of the lightweight model.<\/jats:p>","DOI":"10.3390\/sym12101686","type":"journal-article","created":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T07:23:22Z","timestamp":1602919402000},"page":"1686","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Internal Learning for Image Super-Resolution by Adaptive Feature Transform"],"prefix":"10.3390","volume":"12","author":[{"given":"Yifan","family":"He","sequence":"first","affiliation":[{"name":"School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6582-6423","authenticated-orcid":false,"given":"Xiaofeng","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changlin","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Resources and Environment Information System, Institute of Geographic Sciences and Natural Resources, Chinese Academy of Sciences, Beijing 100864, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TASSP.1978.1163154","article-title":"Cubic splines for image interpolation and digital filtering","volume":"26","author":"Hou","year":"1978","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1109\/83.951537","article-title":"New edge-directed interpolation","volume":"10","author":"Li","year":"2001","journal-title":"IEEE Trans. Image Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/1049-9652(91)90045-L","article-title":"Improving resolution by image registration","volume":"53","author":"Irani","year":"1991","journal-title":"CVGIP Graph. Models Image Process."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5334","DOI":"10.1109\/TIP.2014.2364116","article-title":"Single-image super-resolution via linear mapping of interpolated self-examples","volume":"23","author":"Bevilacqua","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","unstructured":"Sun, J., Xu, Z., and Shum, H.Y. (2008, January 24\u201326). Image super-resolution using gradient profile prior. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AL, USA."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yang, C.Y., Huang, J.B., and Yang, M.H. (2010, January 8\u201312). Exploiting self-similarities for single frame super-resolution. Proceedings of the Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand.","DOI":"10.1007\/978-3-642-19318-7_39"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Timofte, R., De Smet, V., and Van Gool, L. (2013, January 1\u20138). Anchored neighborhood regression for fast example-based super-resolution. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia.","DOI":"10.1109\/ICCV.2013.241"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shi, Y., Wang, K., Xu, L., and Lin, L. (2016, January 11\u201315). Local-and holistic-structure preserving image super resolution via deep joint component learning. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Seattle, WA, USA.","DOI":"10.1109\/ICME.2016.7552908"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.neucom.2016.02.046","article-title":"Incorporating image priors with deep convolutional neural networks for image super-resolution","volume":"194","author":"Liang","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Huang, J.J., Liu, T., Luigi Dragotti, P., and Stathaki, T. (2017, January 21\u201326). SRHRF+: Self-example enhanced single image super-resolution using hierarchical random forests. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.144"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Shocher, A., Cohen, N., and Irani, M. (2018, January 18\u201322). \u201cZero-shot\u201d super-resolution using deep internal learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00329"},{"key":"ref_12","unstructured":"Dong, C., Loy, C.C., He, K., and Tang, X. (2014, January 6\u201312). Image super-resolution using deep convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Zurich, Switzerland."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"Dong","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., and Lee, K.M. (2017, January 21\u201326). Enhanced deep residual networks for single image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lai, W.S., Huang, J.B., Ahuja, N., and Yang, M.H. (2017, January 22\u201325). Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.618"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2599","DOI":"10.1109\/TPAMI.2018.2865304","article-title":"Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks","volume":"41","author":"Lai","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","unstructured":"Wang, Z., Chen, J., and Hoi, S.C. (2019). Deep learning for image super-resolution: A survey. arXiv."},{"key":"ref_18","unstructured":"Anwar, S., Khan, S., and Barnes, N. (2019). A deep journey into super-resolution: A survey. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yang, Y., Wang, Z., Chang, S., Han, W., Yang, J., and Huang, T. (2015, January 7\u201312). Self-tuned deep super resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, USA.","DOI":"10.1109\/CVPRW.2015.7301266"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1944846.1944852","article-title":"Image and video upscaling from local self-examples","volume":"30","author":"Freedman","year":"2011","journal-title":"ACM Trans. Graph. TOG"},{"key":"ref_21","unstructured":"Glasner, D., Bagon, S., and Irani, M. (October, January 29). Super-resolution from a single image. Proceedings of the IEEE Conference on Computer Vision (CVPR), Kyoto, Japan."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3336","DOI":"10.1109\/TIP.2014.2323127","article-title":"Group-based sparse representation for image restoration","volume":"23","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","unstructured":"Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2018, January 18\u201322). Deep image prior. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA."},{"key":"ref_24","unstructured":"Yokota, T., Hontani, H., Zhao, Q., and Cichocki, A. (2019). Manifold Modeling in Embedded Space: A Perspective for Interpreting \u201cDeep Image Prior\u201d. arXiv."},{"key":"ref_25","unstructured":"Timofte, R., Rothe, R., and Van Gool, L. (July, January 26). Seven Ways to Improve Example-Based Single Image Super Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_26","unstructured":"Liang, Y., Timofte, R., Wang, J., Gong, Y., and Zheng, N. (2017). Single image super resolution-when model adaptation matters. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4359","DOI":"10.1109\/TIP.2015.2462113","article-title":"Learning super-resolution jointly from external and internal examples","volume":"24","author":"Wang","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1109\/LSP.2017.2721104","article-title":"Deep CNN-based super-resolution using external and internal examples","volume":"24","author":"Cheong","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., and Courville, A. (2018, January 2\u20137). FiLM: Visual reasoning with a general conditioning layer. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref_31","unstructured":"Tseng, H.Y., Lee, H.Y., Huang, J.B., and Yang, M.H. (2020). Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation. arXiv."},{"key":"ref_32","unstructured":"Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2016). Instance normalization: The missing ingredient for fast stylization. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21\u201326). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Huang, X., and Belongie, S. (2017, January 22\u201329). Arbitrary style transfer in real-time with adaptive instance normalization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"He, J., Dong, C., and Qiao, Y. (2019, January 15\u201321). Modulating image restoration with continual levels via adaptive feature modification layers. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01131"},{"key":"ref_36","unstructured":"Timofte, R., Gu, S., Wu, J., and Van Gool, L. (2018, January 18\u201322). NTIRE 2018 challenge on single image super-resolution: Methods and results. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA."},{"key":"ref_37","unstructured":"Yang, J., Wright, J., Huang, T., and Ma, Y. (2008, January 24\u201326). Image super-resolution as sparse representation of raw image patches. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, AK, USA."},{"key":"ref_38","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_39","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017, December 12). Automatic Differentiation in PyTorch. Available online: https:\/\/openreview.net\/pdf\/25b8eee6c373d48b84e5e9c6e10e7cbbbce4ac73.pdf."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1109\/TIP.2010.2050625","article-title":"Image super-resolution via sparse representation","volume":"19","author":"Yang","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_41","unstructured":"Martin, D., Fowlkes, C., Tal, D., and Malik, J. (2001, January 7\u201314). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Vancouver, BC, Canada."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Huang, J.B., Singh, A., and Ahuja, N. (2015, January 7\u201312). Single image super-resolution from transformed self-exemplars. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J.K., and Lee, K.M. (2015). Accurate image super-resolution using very deep convolutional networks. arXiv.","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., and Fu, Y. (2018, January 8\u201314). Image super-resolution using very deep residual channel attention networks. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Soh, J.W., Cho, S., and Cho, N.I. (2020, January 16\u201318). Meta-Transfer Learning for Zero-Shot Super-Resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00357"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Gu, J., Lu, H., Zuo, W., and Dong, C. (2019, January 15\u201321). Blind super-resolution with iterative kernel correction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00170"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201ccompletely blind\u201d image quality analyzer","volume":"20","author":"Mittal","year":"2012","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/12\/10\/1686\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:21:23Z","timestamp":1760178083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/12\/10\/1686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,14]]},"references-count":47,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["sym12101686"],"URL":"https:\/\/doi.org\/10.3390\/sym12101686","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2020,10,14]]}}}