{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:06:35Z","timestamp":1777993595216,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":57,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609628","type":"print"},{"value":"9789819609635","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0963-5_12","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:46:21Z","timestamp":1733557581000},"page":"202-219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Boosting Few-Shot Detection with\u00a0Large Language Models and\u00a0Layout-to-Image Synthesis"],"prefix":"10.1007","author":[{"given":"Ahmed","family":"Abdullah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolas","family":"Ebert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Wasenm\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"12_CR1","unstructured":"Bansal, H., Grover, A.: Leaving reality to imagination: Robust classification via generated datasets. arXiv preprint 2302.02503 (2023)"},{"key":"12_CR2","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et\u00a0al.: Language models are few-shot learners. In: Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"12_CR4","unstructured":"Cruz, S.D.D., Wasenm\u00fcller, O., Beise, H.P., Stifter, T., Stricker, D.: SVIRO: Synthetic vehicle interior rear seat occupancy dataset and benchmark. In: Winter Conference on Applications of Computer Vision (WACV). pp. 973\u2013982 (2020)"},{"key":"12_CR5","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Ebert, N., Stricker, D., Wasenm\u00fcller, O.: PLG-ViT: Vision transformer with parallel local and global self-attention. Sensors (2023)","DOI":"10.3390\/s23073447"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Ebert, N., Stricker, D., Wasenm\u00fcller, O.: Transformer-based detection of microorganisms on high-resolution petri dish images. In: International Conference on Computer Vision Workshops (ICCVW) (2023)","DOI":"10.1109\/ICCVW60793.2023.00428"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. International Journal of Computer Vision (IJCV) (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"12_CR9","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: Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00129"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Jie, Z., Xie, W., Ma, L.: Instagen: Enhancing object detection by training on synthetic dataset. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01339"},{"key":"12_CR11","unstructured":"Feng, W., Zhu, W., Fu, T.j., Jampani, V., Akula, A., He, X., Basu, S., Wang, X.E., Wang, W.Y.: Layoutgpt: Compositional visual planning and generation with large language models. In: Neural Information Processing Systems (NeurIPS) (2024)"},{"key":"12_CR12","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint 2107.08430 (2021)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Communications of the ACM (2020)","DOI":"10.1145\/3422622"},{"key":"12_CR14","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: A simple data processing method to improve robustness and uncertainty. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: Clipscore: A reference-free evaluation metric for image captioning. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Jia, Y., Hoyer, L., Huang, S., Wang, T., Van\u00a0Gool, L., Schindler, K., Obukhov, A.: Dginstyle: Domain-generalizable semantic segmentation with image diffusion models and stylized semantic control. In: Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2024)","DOI":"10.1007\/978-3-031-72933-1_6"},{"key":"12_CR17","unstructured":"Jiang, A.Q., Sablayrolles, A., Roux, A., Mensch, A., Savary, B., Bamford, C., Chaplot, D.S., Casas, D.d.l., Hanna, E.B., Bressand, F., et\u00a0al.: Mixtral of experts. arXiv preprint 2401.04088 (2024)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00851"},{"key":"12_CR19","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Cheng, Y., Gan, Z., Yu, L., Wang, L., Liu, J.: Bachgan: High-resolution image synthesis from salient object layout. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00839"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., Lee, Y.J.: Gligen: Open-set grounded text-to-image generation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"12_CR23","unstructured":"Li, Y., Keuper, M., Zhang, D., Khoreva, A.: Adversarial supervision makes layout-to-image diffusion models thrive. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"12_CR24","unstructured":"Lian, L., Li, B., Yala, A., Darrell, T.: Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models. arXiv preprint 2305.13655 (2023)"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Lin, S., Wang, K., Zeng, X., Zhao, R.: Explore the power of synthetic data on few-shot object detection. In: Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023)","DOI":"10.1109\/CVPRW59228.2023.00071"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"12_CR28","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint 2310.04378 (2023)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Lv, Z., Wei, Y., Zuo, W., Wong, K.Y.K.: Place: Adaptive layout-semantic fusion for semantic image synthesis. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00885"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Mo, S., Mu, F., Lin, K.H., Liu, Y., Guan, B., Li, Y., Zhou, B.: Freecontrol: Training-free spatial control of any text-to-image diffusion model with any condition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., Shan, Y.: T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In: AAAI conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Oehri, S., Ebert, N., Abdullah, A., Stricker, D., Wasenm\u00fcller, O.: GenFormer - generated images are all you need to improve robustness of transformers on small datasets. In: International Conference on Pattern Recognition (ICPR) (2024)","DOI":"10.1007\/978-3-031-78166-7_12"},{"key":"12_CR33","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"12_CR34","unstructured":"Reichardt, L., Uhr, L., Wasenm\u00fcller, O.: Text3DAug - prompted instance augmentation for lidar perception. In: International Conference on Intelligent Robots and Systems (IROS) (2024)"},{"key":"12_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems (NeurIPS) (2015)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Scheuerman, M.K., Hanna, A., Denton, E.: Do datasets have politics? disciplinary values in computer vision dataset development. Proceedings of the ACM on Human-Computer Interaction (2021)","DOI":"10.1145\/3476058"},{"key":"12_CR38","first-page":"02502","volume":"2010","author":"J Song","year":"2020","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint 2010, 02502 (2020)","journal-title":"Denoising diffusion implicit models. arXiv preprint"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Sun, W., Wu, T.: Image synthesis from reconfigurable layout and style. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01063"},{"key":"12_CR40","unstructured":"Tang, H., Qi, X., Sun, G., Xu, D., Sebe, N., Timofte, R., Van\u00a0Gool, L.: Edge guided gans with contrastive learning for semantic image synthesis. arXiv preprint 2003.13898 (2020)"},{"key":"12_CR41","unstructured":"Wang, X., Huang, T., Gonzalez, J., Darrell, T., Yu, F.: Frustratingly simple few-shot object detection. In: International Conference on Machine Learning (ICML) (2020)"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Darrell, T., Rambhatla, S.S., Girdhar, R., Misra, I.: Instancediffusion: Instance-level control for image generation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Meta-learning to detect rare objects. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01002"},{"key":"12_CR44","unstructured":"Wu, W., Zhao, Y., Chen, H., Gu, Y., Zhao, R., He, Y., Zhou, H., Shou, M.Z., Shen, C.: Datasetdm: Synthesizing data with perception annotations using diffusion models. In: Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., Shou, M.Z.: Boxdiff: Text-to-image synthesis with training-free box-constrained diffusion. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"12_CR46","unstructured":"Xie, J., Ye, K., Li, Y., Li, Y., Lin, K.Q., Zheng, Y., Shen, L., Shou, M.Z.: Visorgpt: Learning visual prior via generative pre-training. arXiv preprint 2305.13777 (2023)"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Xue, H., Huang, Z., Sun, Q., Song, L., Zhang, W.: Freestyle layout-to-image synthesis. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"12_CR49","unstructured":"Yang, L., Xu, X., Kang, B., Shi, Y., Zhao, H.: Freemask: Synthetic images with dense annotations make stronger segmentation models. In: Neural Information Processing Systems (NeurIPS) (2024)"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: Regularization strategy to train strong classifiers with localizable features. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"12_CR52","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.Y.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint 2203.03605 (2022)"},{"key":"12_CR53","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint 1710.09412 (2017)"},{"key":"12_CR54","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":"12_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zheng, Y., Tang, J., Jian, L., Yang, Z.: Flipda: Effective and robust data augmentation for few-shot learning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2022)","DOI":"10.18653\/v1\/2022.acl-long.592"},{"key":"12_CR57","unstructured":"Zhou, Y., Sahak, H., Ba, J.: Training on thin air: Improve image classification with generated data. arXiv preprint 2305.15316 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0963-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:39:11Z","timestamp":1733560751000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0963-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609628","9789819609635"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0963-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","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":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}