{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T10:03:01Z","timestamp":1779703381105,"version":"3.53.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002597","name":"Kyung Hee University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002597","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116216","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T16:17:54Z","timestamp":1779466674000},"page":"116216","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Efficient dataset condensation with learnable color representation and subset matching"],"prefix":"10.1016","volume":"347","author":[{"given":"Linh-Tam","family":"Tran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3758-0902","authenticated-orcid":false,"given":"Quang Hieu","family":"Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0774-5411","authenticated-orcid":false,"given":"Maryam","family":"Qamar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7308-133X","authenticated-orcid":false,"given":"Hui Yong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Ho","family":"Bae","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116216_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113781","article-title":"Drtnet: Dual-route transformer network for thyroid ultrasound segmentation based on bbox-supervised learning","volume":"324","author":"Bi","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116216_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114052","article-title":"Yolo-acr: A new architecture for real-time object detection with advanced feature fusion and bounding box regression","volume":"326","author":"Neri","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116216_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114293","article-title":"Integrated deep learning-based irace and convolutional neural networks for chest x-ray image classification","author":"Abdel Samee","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116216_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113755","article-title":"Hypergraph neural network for remote sensing hyperspectral image super-resolution","volume":"321","author":"Chen","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116216_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113246","article-title":"Asymmetric content-aided transformer for efficient image super-resolution","volume":"315","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116216_b6","series-title":"Dataset distillation","author":"Wang","year":"2018"},{"key":"10.1016\/j.knosys.2026.116216_b7","unstructured":"B. Zhao, K.R. Mopuri, H. Bilen, Dataset condensation with gradient matching, in: International Conference on Learning Representations, 2021, pp. 1\u20139."},{"key":"10.1016\/j.knosys.2026.116216_b8","first-page":"12674","article-title":"Dataset condensation with differentiable siamese augmentation","volume":"Vol. 139","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116216_b9","series-title":"IEEE Conf. Comput. Vis. Pattern Recog.","first-page":"12186","article-title":"Cafe: Learning to condense dataset by aligning features","author":"Wang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116216_b10","unstructured":"J.-H. Kim, J. Kim, S.J. Oh, S. Yun, H. Song, J. Jeong, J.-W. Ha, H.O. Song, Dataset condensation via efficient synthetic-data parameterization, in: Int. Conf. Mach. Learn., 2022, pp. 11102\u201311118."},{"key":"10.1016\/j.knosys.2026.116216_b11","doi-asserted-by":"crossref","unstructured":"G. Cazenavette, T. Wang, A. Torralba, A.A. Efros, J.-Y. Zhu, Dataset distillation by matching training trajectories, in: IEEE Conf. Comput. Vis. Pattern Recog., 2022, pp. 10718\u201310727.","DOI":"10.1109\/CVPR52688.2022.01045"},{"key":"10.1016\/j.knosys.2026.116216_b12","doi-asserted-by":"crossref","unstructured":"B. Zhao, H. Bilen, Dataset condensation with distribution matching, in: IEEE\/CVF Winter Conf. Appl. Comput. Vis., 2023, pp. 6514\u20136523.","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"10.1016\/j.knosys.2026.116216_b13","series-title":"IEEE Conf. Comput. Vis. Pattern Recog.","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.knosys.2026.116216_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112707","article-title":"Revisiting representation learning of color information: Color medical image segmentation incorporating quaternion","volume":"306","author":"Xia","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116216_b15","series-title":"Digital Image Processing","author":"Gonzalez","year":"2002"},{"key":"10.1016\/j.knosys.2026.116216_b16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2018.01.091","article-title":"Segmentation of images by color features: A survey","volume":"292","author":"Garcia-Lamont","year":"2018","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.knosys.2026.116216_b17","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1007\/s10015-005-0352-x","article-title":"An image segmentation method using histograms and the human characteristics of hsi color space for a scene image","volume":"10","author":"Ito","year":"2006","journal-title":"Artif. Life Robot."},{"issue":"12","key":"10.1016\/j.knosys.2026.116216_b18","doi-asserted-by":"crossref","first-page":"2259","DOI":"10.1016\/S0031-3203(00)00149-7","article-title":"Color image segmentation: advances and prospects","volume":"34","author":"Cheng","year":"2001","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116216_b19","first-page":"12352","article-title":"Dataset condensation with contrastive signals","volume":"Vol. 162","author":"Lee","year":"2022"},{"key":"10.1016\/j.knosys.2026.116216_b20","doi-asserted-by":"crossref","unstructured":"G. Zhao, G. Li, Y. Qin, Y. Yu, Improved distribution matching for dataset condensation, in: IEEE Conf. Comput. Vis. Pattern Recog., 2023, pp. 7856\u20137865.","DOI":"10.1109\/CVPR52729.2023.00759"},{"key":"10.1016\/j.knosys.2026.116216_b21","unstructured":"Q.H. Vo, C.S. Hong, Distribution matching with multi-formation function for dataset distillation, in: 2023 24st Asia-Pacific Network Operations and Management Symposium, APNOMS, 2023, pp. 13\u201317."},{"key":"10.1016\/j.knosys.2026.116216_b22","doi-asserted-by":"crossref","unstructured":"J. Du, Y. Jiang, V.Y.F. Tan, J.T. Zhou, H. Li, Minimizing the accumulated trajectory error to improve dataset distillation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 3749\u20133758.","DOI":"10.1109\/CVPR52729.2023.00365"},{"key":"10.1016\/j.knosys.2026.116216_b23","series-title":"Dataset distillation by automatic training trajectories","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116216_b24","doi-asserted-by":"crossref","unstructured":"Y. Liu, J. Gu, K. Wang, Z. Zhu, W. Jiang, Y. You, Dream: Efficient dataset distillation by representative matching, in: Int. Conf. Comput. Vis., 2023, pp. 17314\u201317324.","DOI":"10.1109\/ICCV51070.2023.01588"},{"key":"10.1016\/j.knosys.2026.116216_b25","series-title":"Adv. Neural Inform. Process. Syst.","first-page":"1","article-title":"Dataset distillation using neural feature regression","author":"Zhou","year":"2022"},{"key":"10.1016\/j.knosys.2026.116216_b26","series-title":"IJCNN","first-page":"1","article-title":"Soft-label dataset distillation and text dataset distillation","author":"Sucholutsky","year":"2021"},{"key":"10.1016\/j.knosys.2026.116216_b27","series-title":"Flexible dataset distillation: Learn labels instead of images","author":"Bohdal","year":"2020"},{"issue":"11","key":"10.1016\/j.knosys.2026.116216_b28","first-page":"12217","article-title":"Summarizing stream data for memory-constrained online continual learning","volume":"38","author":"Gu","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116216_b29","series-title":"Federated learning via synthetic data","author":"Goetz","year":"2020"},{"key":"10.1016\/j.knosys.2026.116216_b30","series-title":"Distilled one-shot federated learning","author":"Zhou","year":"2020"},{"issue":"20","key":"10.1016\/j.knosys.2026.116216_b31","first-page":"21904","article-title":"Fedvck: Non-iid robust and communication-efficient federated learning via valuable condensed knowledge for medical image analysis","volume":"39","author":"Yan","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116216_b32","series-title":"The Thirty-Eighth Annual Conference on Neural Information Processing Systems","article-title":"Fetch and forge: Efficient dataset condensation for object detection","author":"Qi","year":"2024"},{"key":"10.1016\/j.knosys.2026.116216_b33","series-title":"Od3: Optimization-free dataset distillation for object detection","author":"Khatib","year":"2025"},{"key":"10.1016\/j.knosys.2026.116216_b34","doi-asserted-by":"crossref","unstructured":"S. Yun, D. Han, S.J. Oh, S. Chun, J. Choe, Y. Yoo, Cutmix: Regularization strategy to train strong classifiers with localizable features, in: Int. Conf. Comput. Vis., 2019.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"10.1016\/j.knosys.2026.116216_b35","unstructured":"B. Zhao, H. Bilen, Synthesizing informative training samples with gan, in: NeurIPS-22 Worksh. Synth. Data for ML., 2022, pp. 1\u201313."},{"key":"10.1016\/j.knosys.2026.116216_b36","doi-asserted-by":"crossref","unstructured":"K. Wang, J. Gu, D. Zhou, Z. Zhu, W. Jiang, Y. You, Dim: Distilling dataset into generative model, in: Eur. Conf. Comput. Vis. Workshop, 2023, pp. 42\u201359.","DOI":"10.1007\/978-3-031-93806-1_4"},{"key":"10.1016\/j.knosys.2026.116216_b37","doi-asserted-by":"crossref","unstructured":"G. Cazenavette, T. Wang, A. Torralba, A.A. Efros, J.-Y. Zhu, Generalizing dataset distillation via deep generative prior, in: IEEE Conf. Comput. Vis. Pattern Recog., 2023, pp. 3739\u20133748.","DOI":"10.1109\/CVPR52729.2023.00364"},{"key":"10.1016\/j.knosys.2026.116216_b38","series-title":"Adv. Neural Inform. Process. Syst.","first-page":"1","article-title":"Efficient dataset distillation using random feature approximation","author":"Loo","year":"2022"},{"key":"10.1016\/j.knosys.2026.116216_b39","unstructured":"Recommendation ITU-R BT.601 standard definition: https:\/\/www.itu.int\/."},{"key":"10.1016\/j.knosys.2026.116216_b40","unstructured":"Recommendation ITU-R BT.709 standard definition: https:\/\/www.itu.int\/."},{"key":"10.1016\/j.knosys.2026.116216_b41","series-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.knosys.2026.116216_b42","series-title":"Adv. Neural Inform. Process. Syst.","first-page":"1","article-title":"PyramidCLIP: Hierarchical feature alignment for vision-language model pretraining","author":"Gao","year":"2022"},{"key":"10.1016\/j.knosys.2026.116216_b43","series-title":"Adv. Neural Inform. Process. Syst.","first-page":"1","article-title":"CyCLIP: Cyclic contrastive language-image pretraining","author":"Goel","year":"2022"},{"key":"10.1016\/j.knosys.2026.116216_b44","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.knosys.2026.116216_b45","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: IEEE Conf. Comput. Vis. Pattern Recog., 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.116216_b46","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. van der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: IEEE Conf. Comput. Vis. Pattern Recog., 2017, pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.knosys.2026.116216_b47","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"Vol. 97","author":"Tan","year":"2019"},{"key":"10.1016\/j.knosys.2026.116216_b48","doi-asserted-by":"crossref","unstructured":"L. Zhang, J. Zhang, B. Lei, S. Mukherjee, X. Pan, B. Zhao, C. Ding, Y. Li, D. Xu, Accelerating dataset distillation via model augmentation, in: IEEE Conf. Comput. Vis. Pattern Recog., 2023, pp. 11950\u201311959.","DOI":"10.1109\/CVPR52729.2023.01150"},{"key":"10.1016\/j.knosys.2026.116216_b49","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.knosys.2026.116216_b50","series-title":"Adv. Neural Inform. Process. Syst.","first-page":"1","article-title":"Squeeze, recover and relabel: Dataset condensation at imagenet scale from a new perspective","author":"Yin","year":"2023"},{"key":"10.1016\/j.knosys.2026.116216_b51","series-title":"IEEE Conf. Comput. Vis. Pattern Recog.","first-page":"9390","article-title":"On the diversity and realism of distilled dataset: An efficient dataset distillation paradigm","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.116216_b52","series-title":"IEEE Conf. Comput. Vis. Pattern Recog.","first-page":"15793","article-title":"Efficient dataset distillation via minimax diffusion","author":"Gu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116216_b53","unstructured":"L. Zhao, Y. Wu, X. Jiang, J. Gu, Y. Wang, X. Xu, P. Zhao, X. Lin, Taming diffusion for dataset distillation with high representativeness, in: Int. Conf. Mach. Learn., 2025, pp. 1\u201321."},{"key":"10.1016\/j.knosys.2026.116216_b54","series-title":"Overcoming catastrophic forgetting in neural networks","author":"Kirkpatrick","year":"2016"},{"issue":"2","key":"10.1016\/j.knosys.2026.116216_b55","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1080\/09540099550039318","article-title":"Catastrophic forgetting, rehearsal and pseudorehearsal","volume":"7","author":"Robins","year":"1995","journal-title":"Connect. Sci."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009421?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009421?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T09:10:39Z","timestamp":1779700239000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":55,"alternative-id":["S0950705126009421"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116216","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Efficient dataset condensation with learnable color representation and subset matching","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116216","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116216"}}