{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T00:40:39Z","timestamp":1701564039853},"reference-count":37,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2023,12,1]]},"DOI":"10.1587\/transinf.2023edp7025","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T22:35:13Z","timestamp":1701383713000},"page":"2085-2096","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Detailed Intermediate Supervision for Image-to-Image Translation"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Jianbo","family":"WANG","sequence":"first","affiliation":[{"name":"The University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozhi","family":"HUANG","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"SHEN","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"WANG","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshihiko","family":"YAMASAKI","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, \u201cGenerative adversarial nets,\u201d Advances in neural information processing systems, pp.2672-2680, 2014."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] P. Isola, J.-Y. Zhu, T. Zhou, and A.A. Efros, \u201cImage-to-image translation with conditional adversarial networks,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1125-1134, 2017. 10.1109\/cvpr.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] J.-Y. Zhu, T. Park, P. Isola, and A.A. Efros, \u201cUnpaired image-to-image translation using cycle-consistent adversarial networks,\u201d Proceedings of the IEEE international conference on computer vision, pp.2223-2232, 2017. 10.1109\/iccv.2017.244","DOI":"10.1109\/ICCV.2017.244"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] T. Karras, S. Laine, and T. Aila, \u201cA style-based generator architecture for generative adversarial networks,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4401-4410, 2019. 10.1109\/cvpr.2019.00453","DOI":"10.1109\/CVPR.2019.00453"},{"key":"5","unstructured":"[5] T. Karras, T. Aila, S. Laine, and J. Lehtinen, \u201cProgressive growing of gans for improved quality, stability, and variation,\u201d arXiv preprint arXiv:1710.10196, 2017."},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] T.-C. Wang, M.-Y. Liu, J.-Y. Zhu, A. Tao, J. Kautz, and B. Catanzaro, \u201cHigh-resolution image synthesis and semantic manipulation with conditional gans,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.8798-8807, 2018. 10.1109\/cvpr.2018.00917","DOI":"10.1109\/CVPR.2018.00917"},{"key":"7","unstructured":"[7] N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F.A. Hamprecht, Y. Bengio, and A. Courville, \u201cOn the spectral bias of neural networks,\u201d arXiv preprint arXiv:1806.08734, 2018."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Z.-Q.J. Xu, Y. Zhang, and Y. Xiao, \u201cTraining behavior of deep neural network in frequency domain,\u201d International Conference on Neural Information Processing, pp.264-274, Springer, 2019. 10.1007\/978-3-030-36708-4_22","DOI":"10.1007\/978-3-030-36708-4_22"},{"key":"9","unstructured":"[9] M.Y. Liu, T. Breuel, and J. Kautz, \u201cUnsupervised image-to-image translation networks,\u201d Advances in neural information processing systems, pp.700-708, 2017."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] X. Huang, M.-Y. Liu, S. Belongie, and J. Kautz, \u201cMultimodal unsupervised image-to-image translation,\u201d Proceedings of the European Conference on Computer Vision (ECCV), pp.179-196, 2018. 10.1007\/978-3-030-01219-9_11","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] T. Park, M.-Y. Liu, T.-C. Wang, and J.-Y. Zhu, \u201cSemantic image synthesis with spatially-adaptive normalization,\u201d Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp.2337-2346, 2019. 10.1109\/cvpr.2019.00244","DOI":"10.1109\/CVPR.2019.00244"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] V. Sushko, E. Sch\u00f6nfeld, D. Zhang, J. Gall, B. Schiele, and A. Khoreva, \u201cOasis: only adversarial supervision for semantic image synthesis,\u201d International Journal of Computer Vision, vol.130, no.12, pp.2903-2923, 2022. 10.1007\/s11263-022-01673-x","DOI":"10.1007\/s11263-022-01673-x"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] L.A. Gatys, A.S. Ecker, and M. Bethge, \u201cImage style transfer using convolutional neural networks,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2414-2423, 2016. 10.1109\/cvpr.2016.265","DOI":"10.1109\/CVPR.2016.265"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] C. Dong, C.C. Loy, K. He, and X. Tang, \u201cImage super-resolution using deep convolutional networks,\u201d IEEE transactions on pattern analysis and machine intelligence, vol.38, no.2, pp.295-307, 2016. 10.1109\/tpami.2015.2439281","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] R.A. Yeh, C. Chen, T.Y. Lim, A.G. Schwing, M. Hasegawa-Johnson, and M.N. Do, \u201cSemantic image inpainting with deep generative models,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.5485-5493, 2017. 10.1109\/cvpr.2017.728","DOI":"10.1109\/CVPR.2017.728"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, \u201cBeyond a gaussian denoiser: Residual learning of deep cnn for image denoising,\u201d IEEE Transactions on Image Processing, vol.26, no.7, pp.3142-3155, 2017. 10.1109\/tip.2017.2662206","DOI":"10.1109\/TIP.2017.2662206"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] P. Burt and E. Adelson, \u201cThe laplacian pyramid as a compact image code,\u201d IEEE Transactions on communications, vol.31, no.4, pp.532-540, 1983. 10.1109\/tcom.1983.1095851","DOI":"10.1109\/TCOM.1983.1095851"},{"key":"18","unstructured":"[18] E.H. Adelson, C.H. Anderson, J.R. Bergen, P.J. Burt, and J.M. Ogden, \u201cPyramid methods in image processing,\u201d RCA engineer, vol.29, no.6, pp.33-41, 1984."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang, \u201cDeep laplacian pyramid networks for fast and accurate super-resolution,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.624-632, 2017. 10.1109\/cvpr.2017.618","DOI":"10.1109\/CVPR.2017.618"},{"key":"20","unstructured":"[20] E.L. Denton, S. Chintala, R. Fergus, <i>et al.<\/i>, \u201cDeep generative image models using a laplacian pyramid of adversarial networks,\u201d Advances in neural information processing systems, pp.1486-1494, 2015."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] J. Liang, H. Zeng, and L. Zhang, \u201cHigh-resolution photorealistic image translation in real-time: A laplacian pyramid translation network,\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.9392-9400, 2021. 10.1109\/cvpr46437.2021.00927","DOI":"10.1109\/CVPR46437.2021.00927"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] L. Cheng, C. Zhang, and Z. Liao, \u201cIntrinsic image transformation via scale space decomposition,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.656-665, 2018. 10.1109\/cvpr.2018.00075","DOI":"10.1109\/CVPR.2018.00075"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] O. Ronneberger, P. Fischer, and T. Brox, \u201cU-net: Convolutional networks for biomedical image segmentation,\u201d International Conference on Medical image computing and computer-assisted intervention, pp.234-241, Springer, 2015. 10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] S. Ravishankar and Y. Bresler, \u201cMR image reconstruction from highly undersampled k-space data by dictionary learning,\u201d IEEE transactions on medical imaging, vol.30, no.5, pp.1028-1041, 2011. 10.1109\/tmi.2010.2090538","DOI":"10.1109\/TMI.2010.2090538"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] C.R.A. Chaitanya, A.S. Kaplanyan, C. Schied, M. Salvi, A. Lefohn, D. Nowrouzezahrai, and T. Aila, \u201cInteractive reconstruction of monte carlo image sequences using a recurrent denoising autoencoder,\u201d ACM Transactions on Graphics (TOG), vol.36, no.4, pp.1-12, 2017. 10.1145\/3072959.3073601","DOI":"10.1145\/3072959.3073601"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] R. Zhang, P. Isola, A.A. Efros, E. Shechtman, and O. Wang, \u201cThe unreasonable effectiveness of deep features as a perceptual metric,\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.586-595, 2018. 10.1109\/cvpr.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"27","unstructured":"[27] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv preprint arXiv:1409.1556, 2014."},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R.Benenson, U. Franke, S. Roth, and B. Schiele, \u201cThe cityscapes dataset for semantic urban scene understanding,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.3213-3223, 2016. 10.1109\/cvpr.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] R. Tyle\u010dek and R. \u0160\u00e1ra, \u201cSpatial pattern templates for recognition of objects with regular structure,\u201d German Conference on Pattern Recognition, pp.364-374, Springer, 2013. 10.1007\/978-3-642-40602-7_39","DOI":"10.1007\/978-3-642-40602-7_39"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] P.-Y. Laffont, Z. Ren, X. Tao, C. Qian, and J. Hays, \u201cTransient attributes for high-level understanding and editing of outdoor scenes,\u201d ACM Transactions on graphics (TOG), vol.33, no.4, pp.1-11, 2014. 10.1145\/2601097.2601101","DOI":"10.1145\/2601097.2601101"},{"key":"31","unstructured":"[31] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014."},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] M. Li, J. Lin, Y. Ding, Z. Liu, J.-Y. Zhu, and S. Han, \u201cGan compression: Efficient architectures for interactive conditional gans,\u201d arXiv preprint arXiv:2003.08936, 2020.","DOI":"10.1109\/CVPR42600.2020.00533"},{"key":"33","unstructured":"[33] D. Ulyanov, A. Vedaldi, and V. Lempitsky, \u201cInstance normalization: The missing ingredient for fast stylization,\u201d arXiv preprint arXiv:1607.08022, 2016."},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"35","doi-asserted-by":"publisher","unstructured":"[35] Z. Wang, A.C. Bovik, H.R. Sheikh, and E.P. Simoncelli, \u201cImage quality assessment: from error visibility to structural similarity,\u201d IEEE transactions on image processing, vol.13, no.4, pp.600-612, 2004. 10.1109\/tip.2003.819861","DOI":"10.1109\/TIP.2003.819861"},{"key":"36","unstructured":"[36] M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, \u201cGans trained by a two time-scale update rule converge to a local nash equilibrium,\u201d Advances in neural information processing systems, pp.6626-6637, 2017."},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] J. Long, E. Shelhamer, and T. Darrell, \u201cFully convolutional networks for semantic segmentation,\u201d Proceedings of the IEEE conference on computer vision and pattern recognition, pp.3431-3440, 2015. 10.1109\/cvpr.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/12\/E106.D_2023EDP7025\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T04:18:40Z","timestamp":1701490720000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/12\/E106.D_2023EDP7025\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":37,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023edp7025","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,1]]},"article-number":"2023EDP7025"}}