{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:52:52Z","timestamp":1781110372546,"version":"3.54.1"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"2s","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Institute of Information and Communication Technology Planning Evaluation","award":["IITP-2019-0-00421"],"award-info":[{"award-number":["IITP-2019-0-00421"]}]},{"name":"Information Technology Research Center","award":["IITP-2021-0-02052"],"award-info":[{"award-number":["IITP-2021-0-02052"]}]},{"name":"ICT Creative Consilience program","award":["IITP-2020-0-01821"],"award-info":[{"award-number":["IITP-2020-0-01821"]}]},{"name":"Artificial Intelligence Innovation Hub program","award":["IITP-2021-0-02068"],"award-info":[{"award-number":["IITP-2021-0-02068"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p>Conventional image compression techniques targeted for the perceptual quality are not generally optimized for classification tasks using deep neural networks (DNNs). To compress images for DNN inference tasks, recent studies have proposed task-centric image compression methods with quantization techniques optimized for DNN inference. Among them, color quantization was proposed to reduce the amount of data per pixel by limiting the number of distinct colors (color space) in an image. However, quantizing images into various color space sizes requires training and inference of multiple DNNs, each of which is dedicated to each color space. To overcome this limitation, we propose a scalable color quantization method, where images with variable color space sizes can be extracted from a master image generated by a single DNN model. This scalability is enabled by weighted color grouping that constructs a color palette using critical color components for the classification task. We also propose an adaptive training method that can jointly optimize images with various color-space sizes. The results show that the proposed method supports dynamic changes of the color space size between 1\u20136 bit color space per pixel, while even increasing the inference accuracy at a low bit precision up to 20.2% and 46.6% compared to other task- and human-centric color quantizations, respectively.<\/jats:p>","DOI":"10.1145\/3551389","type":"journal-article","created":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T11:46:06Z","timestamp":1659354366000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Scalable Color Quantization for Task-centric Image Compression"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1424-372X","authenticated-orcid":false,"given":"Jae Hyun","family":"Park","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1382-1858","authenticated-orcid":false,"given":"Sanghoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Semiconductor and Display Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9398-9089","authenticated-orcid":false,"given":"Joo Chan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4434-4318","authenticated-orcid":false,"given":"Jong Hwan","family":"Ko","sequence":"additional","affiliation":[{"name":"College of Information and Communication Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,17]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1007\/978-1-4471-6684-9_13","volume-title":"Digital Image Processing","author":"Burger Wilhelm","year":"2016","unstructured":"Wilhelm Burger and Mark J. Burge. 2016. Color quantization. In Digital Image Processing. Springer, 329\u2013339."},{"key":"e_1_3_1_3_2","first-page":"163","volume-title":"Data Compression Conference (DCC)","author":"Chamain Lahiru D.","year":"2021","unstructured":"Lahiru D. Chamain, Fabien Racap\u00e9, Jean B\u00e9gaint, Akshay Pushparaja, and Simon Feltman. 2021. End-to-end optimized image compression for machines, a study. In Data Compression Conference (DCC). IEEE, 163\u2013172."},{"key":"e_1_3_1_4_2","first-page":"309","volume-title":"European Conference on Computer Vision","author":"Choi Jinyoung","year":"2020","unstructured":"Jinyoung Choi and Bohyung Han. 2020. Task-aware quantization network for JPEG image compression. In European Conference on Computer Vision. Springer, 309\u2013324."},{"key":"e_1_3_1_5_2","first-page":"215","volume-title":"14th International Conference on Artificial Intelligence and Statistics","author":"Coates Adam","year":"2011","unstructured":"Adam Coates, Andrew Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In 14th International Conference on Artificial Intelligence and Statistics. 215\u2013223."},{"key":"e_1_3_1_6_2","first-page":"21","volume-title":"IEEE International Symposium on Circuits and Systems (ISCAS)","author":"Deng Yining","year":"1999","unstructured":"Yining Deng, Charles Kenney, Michael S. Moore, and B. S. Manjunath. 1999. Peer group filtering and perceptual color image quantization. In IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 21\u201324."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.946985"},{"key":"e_1_3_1_8_2","article-title":"Towards task-generic image compression: A study of semantics-oriented metrics","author":"Gao Changsheng","year":"2021","unstructured":"Changsheng Gao, Dong Liu, Li Li, and Feng Wu. 2021. Towards task-generic image compression: A study of semantics-oriented metrics. IEEE Trans. Multim. (2021).","journal-title":"IEEE Trans. Multim."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-83492-9_20"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(91)90035-N"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(85)90224-5"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/965145.801294"},{"key":"e_1_3_1_14_2","article-title":"Distilling the knowledge in a neural network","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015).","journal-title":"arXiv preprint arXiv:1503.02531"},{"key":"e_1_3_1_15_2","first-page":"10116","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hou Yunzhong","year":"2020","unstructured":"Yunzhong Hou, Liang Zheng, and Stephen Gould. 2020. Learning to structure an image with few colors. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10116\u201310125."},{"key":"e_1_3_1_16_2","first-page":"1138","volume-title":"IEEE Global Telecommunications Conference","author":"Houle G.","year":"1986","unstructured":"G. Houle and E. Dubois. 1986. Quantization of color images for display on graphics terminals. In IEEE Global Telecommunications Conference. 1138\u20131142."},{"key":"e_1_3_1_17_2","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015).","journal-title":"arXiv preprint arXiv:1502.03167"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3108449"},{"key":"e_1_3_1_20_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. https:\/\/www.cs.toronto.edu\/kriz\/learning-features-2009-TR.pdf."},{"key":"e_1_3_1_21_2","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le Ya","year":"2015","unstructured":"Ya Le and Xuan Yang. 2015. Tiny ImageNet visual recognition challenge. CS 231N 7 (2015).","journal-title":"CS 231N"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196022"},{"key":"e_1_3_1_23_2","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016).","journal-title":"arXiv preprint arXiv:1608.03983"},{"key":"e_1_3_1_24_2","unstructured":"ISO\/IEC JTC 1\/SC29\/WG1 N100094. 2022. Coding of Still Pictures - ds.jpeg.org. Retrieved from https:\/\/ds.jpeg.org\/documents\/jpegai\/wg1n90021-REQ-JPEG_AI_Use_Cases_and_Requirements.pdf."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/78.107417"},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","first-page":"1281","DOI":"10.1109\/ICIP40778.2020.9191247","volume-title":"IEEE International Conference on Image Processing (ICIP)","author":"Patwa Neel","year":"2020","unstructured":"Neel Patwa, Nilesh Ahuja, Srinivasa Somayazulu, Omesh Tickoo, Srenivas Varadarajan, and Shashidhar Koolagudi. 2020. Semantic-preserving image compression. In IEEE International Conference on Image Processing (ICIP). IEEE, 1281\u20131285."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_1_29_2","first-page":"618","volume-title":"IEEE International Conference on Computer Vision","author":"Selvaraju Ramprasaath R.","year":"2017","unstructured":"Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-Cam: Visual explanations from deep networks via gradient-based localization. In IEEE International Conference on Computer Vision. 618\u2013626."},{"key":"e_1_3_1_30_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"e_1_3_1_31_2","first-page":"1100612","volume-title":"Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications","author":"Smith Leslie N.","year":"2019","unstructured":"Leslie N. Smith and Nicholay Topin. 2019. Super-convergence: Very fast training of neural networks using large learning rates. In Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, Vol. 11006. International Society for Optics and Photonics, 1100612."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3004967"},{"key":"e_1_3_1_33_2","article-title":"Lossy image compression with recurrent neural networks: From human perceived visual quality to classification accuracy","author":"Weber Maurice","year":"2019","unstructured":"Maurice Weber, Cedric Renggli, Helmut Grabner, and Ce Zhang. 2019. Lossy image compression with recurrent neural networks: From human perceived visual quality to classification accuracy. arXiv preprint arXiv:1910.03472 (2019).","journal-title":"arXiv preprint arXiv:1910.03472"},{"key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1007\/978-3-030-71278-5_10","volume-title":"Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR\u201920","author":"Weber Maurice","year":"2021","unstructured":"Maurice Weber, Cedric Renggli, Helmut Grabner, and Ce Zhang. 2021. Observer dependent lossy image compression. In Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR\u201920, T\u00fcbingen, Germany, September 28\u2013October 1, 2020, Proceedings 42. Springer, 130\u2013144."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/146443.146475"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/256157.256159"},{"key":"e_1_3_1_37_2","article-title":"Any-precision deep neural networks","author":"Yu Haichao","year":"2019","unstructured":"Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang, and Gang Hua. 2019. Any-precision deep neural networks. arXiv preprint arXiv:1911.07346 (2019).","journal-title":"arXiv preprint arXiv:1911.07346"},{"key":"e_1_3_1_38_2","first-page":"1803","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Yu Jiahui","year":"2019","unstructured":"Jiahui Yu and Thomas S. Huang. 2019. Universally slimmable networks and improved training techniques. In IEEE\/CVF International Conference on Computer Vision. 1803\u20131811."},{"key":"e_1_3_1_39_2","article-title":"Precision gating: Improving neural network efficiency with dynamic dual-precision activations","author":"Zhang Yichi","year":"2020","unstructured":"Yichi Zhang, Ritchie Zhao, Weizhe Hua, Nayun Xu, G. Edward Suh, and Zhiru Zhang. 2020. Precision gating: Improving neural network efficiency with dynamic dual-precision activations. arXiv preprint arXiv:2002.07136 (2020).","journal-title":"arXiv preprint arXiv:2002.07136"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551389","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3551389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:25Z","timestamp":1750186825000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":38,"journal-issue":{"issue":"2s","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1145\/3551389"],"URL":"https:\/\/doi.org\/10.1145\/3551389","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"2021-05-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}