{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T03:00:06Z","timestamp":1768532406926,"version":"3.49.0"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726729","type":"print"},{"value":"9783031726736","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"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\/978-3-031-72673-6_25","type":"book-chapter","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T16:03:50Z","timestamp":1729526630000},"page":"455-473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["PYRA: Parallel Yielding Re-activation for\u00a0Training-Inference Efficient Task Adaptation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5233-9466","authenticated-orcid":false,"given":"Yizhe","family":"Xiong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4180-5801","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-6083","authenticated-orcid":false,"given":"Tianxiang","family":"Hao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1390-7424","authenticated-orcid":false,"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8991-9609","authenticated-orcid":false,"given":"Yuesong","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6193-0864","authenticated-orcid":false,"given":"Guoxin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7816-0587","authenticated-orcid":false,"given":"Yongjun","family":"Bao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0137-9975","authenticated-orcid":false,"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, S., Hu, S.X., Damianou, A., Lawrence, N.D., Dai, Z.: Variational information distillation for knowledge transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9163\u20139171 (2019)","DOI":"10.1109\/CVPR.2019.00938"},{"key":"25_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. arXiv preprint arXiv:2210.09461 (2022)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M.W., Keutzer, K.: ZeroQ: a novel zero shot quantization framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13169\u201313178 (2020)","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"25_CR4","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) European Conference on Computer Vision, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chavan, A., Shen, Z., Liu, Z., Liu, Z., Cheng, K.T., Xing, E.P.: Vision transformer slimming: Multi-dimension searching in continuous optimization space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4931\u20134941 (2022)","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: An image is worth 1\/2 tokens after layer 2: plug-and-play inference acceleration for large vision-language models. arXiv preprint arXiv:2403.06764 (2024)","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: DiffRate: differentiable compression rate for efficient vision transformers. arXiv preprint arXiv:2305.17997 (2023)","DOI":"10.1109\/ICCV51070.2023.01574"},{"key":"25_CR9","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., Ge, C., Tong, Z., Wang, J., Song, Y., Wang, J., Luo, P.: AdaptFormer: adapting vision transformers for scalable visual recognition. Adv. Neural. Inf. Process. Syst. 35, 16664\u201316678 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR10","first-page":"19974","volume":"34","author":"T Chen","year":"2021","unstructured":"Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. Adv. Neural. Inf. Process. Syst. 34, 19974\u201319988 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR11","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"25_CR12","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"25_CR13","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Ding, N., et\u00a0al.: Delta tuning: a comprehensive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:2203.06904 (2022)","DOI":"10.21203\/rs.3.rs-1553541\/v1"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Ding, Z., et al.: Exploring structured semantic prior for multi label recognition with incomplete labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3398\u20133407 (2023)","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"25_CR16","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"25_CR17","unstructured":"Hao, T., Chen, H., Guo, Y., Ding, G.: Consolidator: mergeable adapter with grouped connections for visual adaptation. arXiv preprint arXiv:2305.00603 (2023)"},{"key":"25_CR18","unstructured":"Hao, T., Ding, X., Feng, J., Yang, Y., Chen, H., Ding, G.: Quantized prompt for efficient generalization of vision-language models. arXiv preprint arXiv:2407.10704 (2024)"},{"key":"25_CR19","unstructured":"Hao, T., Lyu, M., Chen, H., Zhao, S., Han, J., Ding, G.: Re-parameterized low-rank prompt: generalize a vision-language model within 0.5 k parameters. arXiv preprint arXiv:2312.10813 (2023)"},{"key":"25_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":"25_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"issue":"8","key":"25_CR22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"25_CR23","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"25_CR24","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"25_CR25","unstructured":"Huang, X., Shen, Z., Cheng, K.T.: Variation-aware vision transformer quantization. arXiv preprint arXiv:2307.00331 (2023)"},{"key":"25_CR26","doi-asserted-by":"publisher","unstructured":"Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual Prompt Tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13693. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wu, Q., Lin, C.Y., Yang, Y., Qiu, L.: LLMLingua: compressing prompts for accelerated inference of large language models. arXiv preprint arXiv:2310.05736 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"25_CR28","unstructured":"Jie, S., Deng, Z.H.: Convolutional bypasses are better vision transformer adapters. arXiv preprint arXiv:2207.07039 (2022)"},{"key":"25_CR29","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"25_CR30","doi-asserted-by":"publisher","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via latency-aware soft token pruning. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, 23-27 October 2022, Proceedings, Part XI. LNCS, vol. 13671, pp. 620\u2013640. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Kong, Z., et\u00a0al.: SPViT: enabling faster vision transformers via soft token pruning. arXiv preprint arXiv:2112.13890 (2021)","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"25_CR34","first-page":"34451","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Xu, S., Zhang, B., Cao, X., Gao, P., Guo, G.: Q-ViT: accurate and fully quantized low-bit vision transformer. Adv. Neural. Inf. Process. Syst. 35, 34451\u201334463 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR35","doi-asserted-by":"publisher","unstructured":"Li, Y., Adamczewski, K., Li, W., Gu, S., Timofte, R., Gool, L.V.: Revisiting random channel pruning for neural network compression. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18-24 June 2022, pp. 191\u2013201. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00029","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"25_CR36","first-page":"109","volume":"35","author":"D Lian","year":"2022","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: a new baseline for efficient model tuning. Adv. Neural. Inf. Process. Syst. 35, 109\u2013123 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR37","unstructured":"Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR38","unstructured":"Lin, Z., Courbariaux, M., Memisevic, R., Bengio, Y.: Neural networks with few multiplications. arXiv preprint arXiv:1510.03009 (2015)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-tuning V2: prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_CR41","first-page":"28092","volume":"34","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Wang, Y., Han, K., Zhang, W., Ma, S., Gao, W.: Post-training quantization for vision transformer. Adv. Neural. Inf. Process. Syst. 34, 28092\u201328103 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Lyu, M., et al.: One-dimensional adapter to rule them all: Concepts, diffusion models and erasing applications. arXiv preprint arXiv:2312.16145 (2023)","DOI":"10.1109\/CVPR52733.2024.00722"},{"key":"25_CR43","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers. arXiv preprint arXiv:2110.03860 (2021)"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De\u00a0Vries, H., Dumoulin, V., Courville, A.: Film: Visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., Cho, K., Gurevych, I.: AdapterFusion: Non-destructive task composition for transfer learning. arXiv preprint arXiv:2005.00247 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhou, Q., Li, X., Fan, D.P., Lu, X., Ma, L.: BA-SAM: scalable bias-mode attention mask for segment anything model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3162\u20133173 (2024)","DOI":"10.1109\/CVPR52733.2024.00305"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Song, Z., Jia, C., Yang, L., Wei, H., Liu, L.: GraphAlign++: an accurate feature alignment by graph matching for multi-modal 3D object detection. IEEE Trans. Circ. Syst. Video Technol. 34, 2619\u20132632 (2023)","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Song, Z., Wei, H., Bai, L., Yang, L., Jia, C.: GraphAlign: enhancing accurate feature alignment by graph matching for multi-modal 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3358\u20133369 (2023)","DOI":"10.1109\/ICCV51070.2023.00311"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"issue":"5","key":"25_CR50","doi-asserted-by":"publisher","first-page":"4637","DOI":"10.1007\/s11760-024-03101-8","volume":"18","author":"L Tian","year":"2024","unstructured":"Tian, L., Ye, M., Zhou, L., He, Q.: Clip-guided black-box domain adaptation of image classification. SIViP 18(5), 4637\u20134646 (2024)","journal-title":"SIViP"},{"key":"25_CR51","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1365\u20131374 (2019)","DOI":"10.1109\/ICCV.2019.00145"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Lin, Z., Pu, H., Ding, G.: RepViT: revisiting mobile CNN from ViT perspective. arXiv preprint arXiv:2307.09283 (2023)","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"25_CR54","unstructured":"Wang, A., Chen, H., Lin, Z., Zhao, S., Han, J., Ding, G.: CAIT: triple-win compression towards high accuracy, fast inference, and favorable transferability for ViTs. arXiv preprint arXiv:2309.15755 (2023)"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"25_CR56","first-page":"13974","volume":"35","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Luo, H., Wang, P., Ding, F., Wang, F., Li, H.: VTC-LFC: vision transformer compression with low-frequency components. Adv. Neural. Inf. Process. Syst. 35, 13974\u201313988 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Wei, K., et al.: Video event extraction with multi-view interaction knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 19224\u201319233 (2024)","DOI":"10.1609\/aaai.v38i17.29891"},{"issue":"5","key":"25_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3582261","volume":"23","author":"K Wei","year":"2024","unstructured":"Wei, K., et al.: More than syntaxes: Investigating semantics to zero-shot cross-lingual relation extraction and event argument role labelling. ACM Trans. Asian Low-Resour. Lang. Inform. Process. 23(5), 1\u201321 (2024)","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inform. Process."},{"key":"25_CR59","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Chen, H., Lin, Z., Zhao, S., Ding, G.: Confidence-based visual dispersal for few-shot unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11621\u201311631 (2023)","DOI":"10.1109\/ICCV51070.2023.01067"},{"key":"25_CR61","unstructured":"Xiong, Y., et al.: Temporal scaling law for large language models. arXiv preprint arXiv:2404.17785 (2024)"},{"key":"25_CR62","unstructured":"Xu, L., Xie, H., Qin, S.Z.J., Tao, X., Wang, F.L.: Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment. arXiv preprint arXiv:2312.12148 (2023)"},{"key":"25_CR63","first-page":"27168","volume":"35","author":"Z Yao","year":"2022","unstructured":"Yao, Z., Yazdani Aminabadi, R., Zhang, M., Wu, X., Li, C., He, Y.: ZeroQuant: efficient and affordable post-training quantization for large-scale transformers. Adv. Neural. Inf. Process. Syst. 35, 27168\u201327183 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR64","unstructured":"Yu, S., et al.: Unified visual transformer compression. arXiv preprint arXiv:2203.08243 (2022)"},{"key":"25_CR65","unstructured":"Zaken, E.B., Ravfogel, S., Goldberg, Y.: BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)"},{"key":"25_CR66","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"25_CR67","unstructured":"Zhai, X., et\u00a0al.: A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867 (2019)"},{"key":"25_CR68","first-page":"873","volume":"133","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Qiu, L., Zhu, Y., Wen, L., Luo, X.: A new childhood pneumonia diagnosis method based on fine-grained convolutional neural network. Comput. Model. Eng. Sci. 133, 873\u2013894 (2022)","journal-title":"Comput. Model. Eng. Sci."},{"key":"25_CR69","unstructured":"Zhang, Y., Zhou, K., Liu, Z.: Neural prompt search. arXiv preprint arXiv:2206.04673 (2022)"},{"key":"25_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"25_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, F., et al.: Rethinking impersonation and dodging attacks on face recognition systems. In: Proceedings of the 30th ACM International Conference on Multimedia (ACM MM) (2024)","DOI":"10.1145\/3664647.3681440"},{"issue":"2","key":"25_CR72","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1109\/TCSVT.2022.3206476","volume":"33","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q., et al.: Context-aware mixup for domain adaptive semantic segmentation. IEEE Trans. Circuits Syst. Video Technol. 33(2), 804\u2013817 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR73","unstructured":"Zhu, M., Tang, Y., Han, K.: Vision transformer pruning. arXiv preprint arXiv:2104.08500 (2021)"},{"key":"25_CR74","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72673-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:04:20Z","timestamp":1732925060000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72673-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,22]]},"ISBN":["9783031726729","9783031726736"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72673-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,22]]},"assertion":[{"value":"22 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}