{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:59:55Z","timestamp":1762491595174,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093202","type":"print"},{"value":"9783032093219","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-09321-9_30","type":"book-chapter","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:57:45Z","timestamp":1762491465000},"page":"433-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["R&D: Balancing Reliability and\u00a0Diversity in\u00a0Synthetic Data Augmentation for\u00a0Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7477-4702","authenticated-orcid":false,"given":"Huy","family":"Che","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinh-Duy","family":"Phan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2711-1408","authenticated-orcid":false,"given":"Duc-Khai","family":"Lam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput, Vis. (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: 2020 Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Saran, M., Nar, F., Saran, A.N.: Perlin random erasing for data augmentation. In: 29th Signal Processing and Communications Applications Conference (2021)","DOI":"10.1109\/SIU53274.2021.9477804"},{"key":"30_CR6","unstructured":"Chen, Y., et al.: Dynamic scale training for object detection (2021)"},{"key":"30_CR7","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"},{"key":"30_CR8","unstructured":"Wu, W., et al.: DatasetDM: synthesizing data with perception annotations using diffusion models. In: Conference on Neural Information Processing Systems (2023)"},{"key":"30_CR9","unstructured":"Nguyen, Q.H., Vu, T.T., Tran, A.T., Nguyen, K.: Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: Diffumask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. In: Proceedings of International Conference on Computer Vision (ICCV 2023) (2023)","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Che, Q., Le, D., Pham, B., Lam, D., Nguyen, V.: Enhanced generative data augmentation for semantic segmentation via stronger guidance. In: Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - ICPRAM (2025)","DOI":"10.5220\/0013175900003905"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Feng, C.-M., Yu, K., Liu, Y., Khan, S.A., Zuo, W.: Diverse data augmentation with diffusions for effective test-time prompt tuning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"30_CR13","unstructured":"Trabucco, B., Doherty, K., Gurinas, M.A., Salakhutdinov, R.: Effective data augmentation with diffusion models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Fang, H., Han, B., Zhang, S., Zhou, S., Hu, C., Ye, W.-M.: Data augmentation for object detection via controllable diffusion models. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00129"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. ACM. Commun (2020)","DOI":"10.1145\/3422622"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"30_CR17","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: International Conference on Learning Representations (2024)"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Thirty-Eighth AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Kupyn, O., Rupprecht, C.: Dataset enhancement with instance-level augmentations. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73337-6_22"},{"key":"30_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"30_CR22","unstructured":"Damian0815, Compel: A library for conditioning and weighting in prompt-based models (2023). https:\/\/github.com\/damian0815\/compel"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Semi-supervised semantic segmentation using unreliable pseudo-labels. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"30_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Che, Q.-H., Nguyen, D.-P., Pham, M.-Q., Lam, D.-K.: Twinlitenet: an efficient and lightweight model for driveable area and lane segmentation in self-driving cars. In: 2023 International Conference on Multimedia Analysis and Pattern Recognition (MAPR) (2023)","DOI":"10.1109\/MAPR59823.2023.10288646"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Yoshihashi, R., Otsuka, Y., Doi, K., Tanaka, T., Kataoka, H.: Exploring limits of diffusion-synthetic training with weakly supervised semantic segmentation. In: 17th Asian Conference on Computer Vision (2024)","DOI":"10.1007\/978-981-96-0917-8_10"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09321-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T04:58:03Z","timestamp":1762491483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09321-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,8]]},"ISBN":["9783032093202","9783032093219"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09321-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,8]]},"assertion":[{"value":"8 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}