{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T05:22:52Z","timestamp":1733548972171,"version":"3.30.1"},"reference-count":34,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2024,12,1]]},"DOI":"10.1587\/transinf.2024edp7016","type":"journal-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T22:11:37Z","timestamp":1721945497000},"page":"1517-1528","source":"Crossref","is-referenced-by-count":0,"title":["Degraded Image Classification using Knowledge Distillation and Robust Data Augmentations"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Dinesh","family":"DAULTANI","sequence":"first","affiliation":[{"name":"Department of Systems and Control Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"TANAKA","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masatoshi","family":"OKUTOMI","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuki","family":"ENDO","sequence":"additional","affiliation":[{"name":"Department of Business, Teikyo Heisei University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] N. Buch, S.A. Velastin, and J. Orwell, \u201cA review of computer vision techniques for the analysis of urban traffic,\u201d IEEE Trans. Intell. Transp. Syst., vol.12, no.3, pp.920-939, 2011. 10.1109\/tits.2011.2119372","DOI":"10.1109\/TITS.2011.2119372"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] J. Janai, F. G\u00fcney, A. Behl, and A. Geiger, \u201cComputer vision for autonomous vehicles: Problems, datasets and state-of-the-art,\u201d Found. Trends Comput. Graph. Vis., vol.12, no.1-3, pp.1-308, 2017. 10.1561\/0600000079","DOI":"10.1561\/0600000079"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] A. Esteva, K. Chou, S. Yeung, N.V. Naik, A. Madani, A. Mottaghi, Y. Liu, E.J. Topol, J. Dean, and R. Socher, \u201cDeep learning-enabled medical computer vision,\u201d NPJ Digital Medicine, vol.4, no.1, 2021. 10.1038\/s41746-020-00376-2","DOI":"10.1038\/s41746-020-00376-2"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] H. Tian, T. Wang, Y. Liu, X. Qiao, and Y. Li, \u201cComputer vision technology in agricultural automation \u2014 A review,\u201d Information Processing in Agriculture, vol.7, no.1, pp.1-19, 2020. 10.1016\/j.inpa.2019.09.006","DOI":"10.1016\/j.inpa.2019.09.006"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] D.I. Patr\u00edcio and R. Rieder, \u201cComputer vision and artificial intelligence in precision agriculture for grain crops: A systematic review,\u201d Comput. Electron. Agric., vol.153, pp.69-81, 2018. 10.1016\/j.compag.2018.08.001","DOI":"10.1016\/j.compag.2018.08.001"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] Y. Wei, S.N. Tran, S. Xu, B.H. Kang, and M. Springer, \u201cDeep learning for retail product recognition: Challenges and techniques,\u201d Computational Intelligence and Neuroscience, vol.2020, pp.1-23, 2020. 10.1155\/2020\/8875910","DOI":"10.1155\/2020\/8875910"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] J. Yang, S. Li, Z. Wang, H. Dong, J. Wang, and S. Tang, \u201cUsing deep learning to detect defects in manufacturing: A comprehensive survey and current challenges,\u201d Materials, vol.13, no.24, 2020. 10.3390\/ma13245755","DOI":"10.3390\/ma13245755"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] S.P. Mohanty, J. Czakon, K.A. Kaczmarek, A. Pyskir, P. Tarasiewicz, S. Kunwar, J. Rohrbach, D. Luo, M. Prasad, S. Fleer, J.P. G\u00f6pfert, A. Tandon, G. Mollard, N. Rayaprolu, M. Salathe, and M. Schilling, \u201cDeep learning for understanding satellite imagery: An experimental survey,\u201d Frontiers in Artificial Intelligence, vol.3, 2020. 10.3389\/frai.2020.534696","DOI":"10.3389\/frai.2020.534696"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] D. Daultani, M. Tanaka, M. Okutomi, and K. Endo, \u201cILIAC: Efficient classification of degraded images using knowledge distillation with cutout data augmentation,\u201d Electronic Imaging, vol.35, no.9, pp.296-1-296-6, 2023. 10.2352\/ei.2023.35.9.ipas-296","DOI":"10.2352\/EI.2023.35.9.IPAS-296"},{"key":"10","unstructured":"[10] T. Devries and G.W. Taylor, \u201cImproved regularization of convolutional neural networks with cutout,\u201d ArXiv, vol.abs\/1708.04552, 2017."},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang, \u201cRandom erasing data augmentation,\u201d Proceedings of the AAAI Conference on Artificial Intelligence, vol.34, no.07, pp.13001-13008, Apr. 2020. 10.1609\/aaai.v34i07.7000","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] E.D. Cubuk, B. Zoph, J. Shlens, and Q. Le, \u201cRandaugment: Practical automated data augmentation with a reduced search space,\u201d Advances in Neural Information Processing Systems, pp.18613-18624, 2020. 10.1109\/cvprw50498.2020.00359","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] D. Cai, K. Chen, Y. Qian, and J.K. K\u00e4m\u00e4r\u00e4inen, \u201cConvolutional low-resolution fine-grained classification,\u201d Pattern Recognition Letters, vol.119, pp.166-171, 2019. Deep Learning for Pattern Recognition. 10.1016\/j.patrec.2017.10.020","DOI":"10.1016\/j.patrec.2017.10.020"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] T. Son, J. Kang, N. Kim, S. Cho, and S. Kwak, `URIE: Universal image enhancement for visual recognition in the wild,\u201d ECCV, pp.749-765, 2020. 10.1007\/978-3-030-58545-7_43","DOI":"10.1007\/978-3-030-58545-7_43"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] Y. Pei, Y. Huang, Q. Zou, X. Zhang, and S. Wang, \u201cEffects of image degradation and degradation removal to cnn-based image classification,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.43, no.4, pp.1239-1253, 2019. 10.1109\/tpami.2019.2950923","DOI":"10.1109\/TPAMI.2019.2950923"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Y. Wang, Y. Cao, Z.-J. Zha, J. Zhang, and Z. Xiong, \u201cDeep degradation prior for low-quality image classification,\u201d 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.11046-11055, 2020. 10.1109\/cvpr42600.2020.01106","DOI":"10.1109\/CVPR42600.2020.01106"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] Y. Pei, Y. Huang, and X. Zhang, \u201cConsistency guided network for degraded image classification,\u201d IEEE Trans. Circuits Syst. Video Technol., vol.31, no.6, pp.2231-2246, 2021. 10.1109\/tcsvt.2020.3016863","DOI":"10.1109\/TCSVT.2020.3016863"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Z. Yang, W. Dong, X. Li, M. Huang, Y. Sun, and G. Shi, \u201cVector quantization with self-attention for quality-independent representation learning,\u201d 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, pp.24438-24448, IEEE Computer Society, June 2023. 10.1109\/cvpr52729.2023.02341","DOI":"10.1109\/CVPR52729.2023.02341"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] K. Endo, M. Tanaka, and M. Okutomi, \u201cCnn-based classification of degraded images with awareness of degradation levels,\u201d IEEE Trans. Circuits Syst. Video Technol., vol.31, no.10, pp.4046-4057, 2021. 10.1109\/tcsvt.2020.3045659","DOI":"10.1109\/TCSVT.2020.3045659"},{"key":"20","doi-asserted-by":"publisher","unstructured":"[20] K. Endo, M. Tanaka, and M. Okutomi, \u201cCNN-based classification of degraded images without sacrificing clean images,\u201d IEEE Access, vol.9, pp.116094-116104, 2021. 10.1109\/access.2021.3105957","DOI":"10.1109\/ACCESS.2021.3105957"},{"key":"21","unstructured":"[21] S. Yang, W.T. Xiao, M. Zhang, S. Guo, J. Zhao, and S. Furao, \u201cImage data augmentation for deep learning: A survey,\u201d ArXiv, vol.abs\/2204.08610, 2022."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] E.D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q.V. Le, \u201cAutoaugment: Learning augmentation policies from data,\u201d 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.113-123, 2019. 10.1109\/cvpr.2019.00020","DOI":"10.1109\/CVPR.2019.00020"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, and L. Fei-Fei, \u201c \u201cImageNet Large Scale Visual Recognition Challenge,\u201d International Journal of Computer Vision (IJCV), vol.115, no.3, pp.211-252, 2015. 10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"24","unstructured":"[24] H. Naveed, \u201cSurvey: Image mixing and deleting for data augmentation,\u201d ArXiv, vol.abs\/2106.07085, 2021."},{"key":"25","unstructured":"[25] G.E. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network,\u201d ArXiv, vol.abs\/1503.02531, 2015."},{"key":"26","unstructured":"[26] H. Wang, S. Lohit, M.J. Jones, and Y. Fu, \u201cWhat makes a \u201dgood\u201d data augmentation in knowledge distillation-a statistical perspective,\u201d Advances in Neural Information Processing Systems, ed. A.H. Oh, A. Agarwal, D. Belgrave, and K. Cho, 2022."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] S. Yun, D. Han, S.J. Oh, S. Chun, J. Choe, and Y.J. Yoo, \u201cCutMix: Regularization strategy to train strong classifiers with localizable features,\u201d 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp.6022-6031, 2019. 10.1109\/iccv.2019.00612","DOI":"10.1109\/ICCV.2019.00612"},{"key":"28","unstructured":"[28] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, \u201cPytorch: An imperative style, high-performance deep learning library,\u201d Advances in Neural Information Processing Systems 32, pp.8024-8035, Curran Associates, Inc., 2019."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] 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), pp.770-778, 2015. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] D. Han, J. Kim, and J. Kim, \u201cDeep pyramidal residual networks,\u201d 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.6307-6315, 2017. 10.1109\/cvpr.2017.668","DOI":"10.1109\/CVPR.2017.668"},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] Y. Yamada, M. Iwamura, T. Akiba, and K. Kise, \u201cShakedrop regularization for deep residual learning,\u201d IEEE Access, vol.7, pp.186126-186136, 2019. 10.1109\/access.2019.2960566","DOI":"10.1109\/ACCESS.2019.2960566"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] K. Endo, M. Tanaka, and M. Okutomi, \u201cCNN-based classification of degraded images,\u201d Electronic Imaging, vol.2020, no.10, pp.28-1-28-7, 2020. 10.2352\/issn.2470-1173.2020.10.ipas-028","DOI":"10.2352\/ISSN.2470-1173.2020.10.IPAS-028"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] K. Endo, M. Tanaka, and M. Okutomi, \u201cClassifying degraded images over various levels of degradation,\u201d 2020 IEEE International Conference on Image Processing (ICIP), pp.1691-1695, 2020. 10.1109\/icip40778.2020.9191087","DOI":"10.1109\/ICIP40778.2020.9191087"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] D. Daultani and H. Larochelle, \u201cConsolidating separate degradations model via weights fusion and distillation,\u201d Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, pp.440-449, January 2024. 10.1109\/wacvw60836.2024.00053","DOI":"10.1109\/WACVW60836.2024.00053"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/12\/E107.D_2024EDP7016\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T03:25:15Z","timestamp":1733541915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/12\/E107.D_2024EDP7016\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":34,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7016","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"article-number":"2024EDP7016"}}