{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:25:49Z","timestamp":1742919949406,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":50,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609659"},{"type":"electronic","value":"9789819609666"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0966-6_18","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T08:39:51Z","timestamp":1733474391000},"page":"297-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Prompting for\u00a0Diffusion Classifiers"],"prefix":"10.1007","author":[{"given":"Wenxin","family":"Ning","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongliang","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kongming","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"18_CR1","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)"},{"key":"18_CR2","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126 (2021)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Basu, S., Hu, S., Massiceti, D., Feizi, S.: Strong baselines for parameter-efficient few-shot fine-tuning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 11024\u201311031 (2024)","DOI":"10.1609\/aaai.v38i10.28978"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Bose, S., Jha, A., Fini, E., Singha, M., Ricci, E., Banerjee, B.: Stylip: Multi-scale style-conditioned prompt learning for clip-based domain generalization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 5542\u20135552 (2024)","DOI":"10.1109\/WACV57701.2024.00545"},{"key":"18_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"4683","DOI":"10.1109\/TIP.2020.2973812","volume":"29","author":"D Chang","year":"2020","unstructured":"Chang, D., Ding, Y., Xie, J., Bhunia, A.K., Li, X., Ma, Z., Wu, M., Guo, J., Song, Y.Z.: The devil is in the channels: Mutual-channel loss for fine-grained image classification. IEEE Trans. Image Process. 29, 4683\u20134695 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chang, D., Pang, K., Zheng, Y., Ma, Z., Song, Y.Z., Guo, J.: Your\" flamingo\" is my\" bird\": Fine-grained, or not. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11476\u201311485 (2021)","DOI":"10.1109\/CVPR46437.2021.01131"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chang, D., Tong, Y., Du, R., Hospedales, T., Song, Y.Z., Ma, Z.: An erudite fine-grained visual classification model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7268\u20137277 (2023)","DOI":"10.1109\/CVPR52729.2023.00702"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, P., Liu, J., Qian, Y.: Label relation graphs enhanced hierarchical residual network for hierarchical multi-granularity classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4858\u20134867 (2022)","DOI":"10.1109\/CVPR52688.2022.00481"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Chang, D., Xie, J., Du, R., Ma, Z.: Cross-layer feature based multi-granularity visual classification. In: 2022 IEEE International Conference on Visual Communications and Image Processing (VCIP). pp.\u00a01\u20135. IEEE (2022)","DOI":"10.1109\/VCIP56404.2022.10008879"},{"key":"18_CR11","unstructured":"Clark, K., Jaini, P.: Text-to-image diffusion models are zero shot classifiers. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"18_CR12","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR13","unstructured":"Donahue, J., Kr\u00e4henb\u00fchl, P., Darrell, T.: Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)"},{"key":"18_CR14","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Du, R., Chang, D., Hospedales, T., Song, Y.Z., Ma, Z.: Demofusion: Democratising high-resolution image generation with no \\$\\$\\$. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6159\u20136168 (2024)","DOI":"10.1109\/CVPR52733.2024.00589"},{"key":"18_CR16","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., Cohen-Or, D.: An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Ge, C., Huang, R., Xie, M., Lai, Z., Song, S., Li, S., Huang, G.: Domain adaptation via prompt learning. IEEE Transactions on Neural Networks and Learning Systems (2023)","DOI":"10.1109\/TNNLS.2023.3327962"},{"issue":"11","key":"18_CR18","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R., Jacobsen, J.H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., Wichmann, F.A.: Shortcut learning in deep neural networks. Nature Machine Intelligence 2(11), 665\u2013673 (2020)","journal-title":"Nature Machine Intelligence"},{"key":"18_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100285","volume":"38","author":"G Harshvardhan","year":"2020","unstructured":"Harshvardhan, G., Gourisaria, M.K., Pandey, M., Rautaray, S.S.: A comprehensive survey and analysis of generative models in machine learning. Computer Science Review 38, 100285 (2020)","journal-title":"Computer Science Review"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR22","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)"},{"key":"18_CR23","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., M\u00fcller, N., Novotny, D., Tseng, H.Y., Richardt, C., Zollh\u00f6fer, M., Nie\u00dfner, M., et\u00a0al.: Viewdiff: 3d-consistent image generation with text-to-image models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5043\u20135052 (2024)","DOI":"10.1109\/CVPR52733.2024.00482"},{"key":"18_CR25","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De\u00a0Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for nlp. In: International conference on machine learning. pp. 2790\u20132799. PMLR (2019)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Islam, K., Zaheer, M.Z., Mahmood, A., Nandakumar, K.: Diffusemix: Label-preserving data augmentation with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 27621\u201327630 (2024)","DOI":"10.1109\/CVPR52733.2024.02608"},{"key":"18_CR27","first-page":"1022","volume":"34","author":"R Karimi Mahabadi","year":"2021","unstructured":"Karimi Mahabadi, R., Henderson, J., Ruder, S.: Compacter: Efficient low-rank hypercomplex adapter layers. Adv. Neural. Inf. Process. Syst. 34, 1022\u20131035 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR28","unstructured":"Kim, M., Hospedales, T.: Bayestune: Bayesian sparse deep model fine-tuning. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"18_CR29","unstructured":"Koh, P.W., Sagawa, S., Marklund, H., Xie, S.M., Zhang, M., Balsubramani, A., Hu, W., Yasunaga, M., Phillips, R.L., Gao, I., et\u00a0al.: Wilds: A benchmark of in-the-wild distribution shifts. In: International conference on machine learning. pp. 5637\u20135664. PMLR (2021)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: Proceedings of the IEEE international conference on computer vision workshops. pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"18_CR31","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2206\u20132217 (2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"18_CR33","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International conference on machine learning. pp. 12888\u201312900. PMLR (2022)"},{"key":"18_CR34","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"18_CR35","unstructured":"Nayak, N.V., Yu, P., Bach, S.H.: Learning to compose soft prompts for compositional zero-shot learning. arXiv preprint arXiv:2204.03574 (2022)"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: 2012 IEEE conference on computer vision and pattern recognition. pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"18_CR38","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. pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR39","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"18_CR40","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. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., Norouzi, M.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 conference proceedings. pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"issue":"3","key":"18_CR42","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1109\/TNNLS.2018.2852721","volume":"30","author":"W Shi","year":"2018","unstructured":"Shi, W., Gong, Y., Tao, X., Cheng, D., Zheng, N.: Fine-grained image classification using modified dcnns trained by cascaded softmax and generalized large-margin losses. IEEE transactions on neural networks and learning systems 30(3), 683\u2013694 (2018)","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Singh, M., Duval, Q., Alwala, K.V., Fan, H., Aggarwal, V., Adcock, A., Joulin, A., Doll\u00e1r, P., Feichtenhofer, C., Girshick, R., et\u00a0al.: The effectiveness of mae pre-pretraining for billion-scale pretraining. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5484\u20135494 (2023)","DOI":"10.1109\/ICCV51070.2023.00505"},{"key":"18_CR44","unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944 (2023)"},{"key":"18_CR45","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Wang, S., Chen, X., Wang, Y., Long, M., Wang, J.: Progressive adversarial networks for fine-grained domain adaptation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 9213\u20139222 (2020)","DOI":"10.1109\/CVPR42600.2020.00923"},{"key":"18_CR47","unstructured":"Wang, Z., Jiang, Y., Zheng, H., Wang, P., He, P., Wang, Z., Chen, W., Zhou, M., et\u00a0al.: Patch diffusion: Faster and more data-efficient training of diffusion models. Advances in neural information processing systems 36 (2024)"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Yu, T., Xiao, T., Stone, A., Tompson, J., Brohan, A., Wang, S., Singh, J., Tan, C., Peralta, J., Ichter, B., et\u00a0al.: Scaling robot learning with semantically imagined experience. arXiv preprint arXiv:2302.11550 (2023)","DOI":"10.15607\/RSS.2023.XIX.027"},{"issue":"9","key":"18_CR50","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"}],"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\/978-981-96-0966-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T09:08:18Z","timestamp":1733476098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0966-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609659","9789819609666"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0966-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 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"}}]}}