{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:33:55Z","timestamp":1780500835666,"version":"3.54.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726392","type":"print"},{"value":"9783031726408","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72640-8_5","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"76-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Token Compensator: Altering Inference Cost of\u00a0Vision Transformer Without Re-tuning"],"prefix":"10.1007","author":[{"given":"Shibo","family":"Jie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehui","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyuan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Hong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"5_CR1","unstructured":"Bolya, D., Fu, C., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: Your vit but faster. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=JroZRaRw7Eu"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"Chavan, A., Shen, Z., Liu, Z., Liu, Z., Cheng, K., Xing, E.P.: Vision transformer slimming: multi-dimension searching in continuous optimization space. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp. 4921\u20134931. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00488","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"5_CR3","doi-asserted-by":"publisher","unstructured":"Chen, M., et al.: Diffrate: differentiable compression rate for efficient vision transformers. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 17118\u201317128. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01574","DOI":"10.1109\/ICCV51070.2023.01574"},{"key":"5_CR4","unstructured":"Chen, S., et al.: Adaptformer: adapting vision transformers for scalable visual recognition. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022 (2022). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/69e2f49ab0837b71b0e0cb7c555990f8-Abstract-Conference.html"},{"key":"5_CR5","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=plKu2GByCNW"},{"key":"5_CR6","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20-25 June 2009, Miami, Florida, USA, pp. 248\u2013255. IEEE Computer Society (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Ding, N., Tang, Y., Han, K., Xu, C., Wang, Y.: Network expansion for practical training acceleration. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pp. 20269\u201320279. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01941","DOI":"10.1109\/CVPR52729.2023.01941"},{"key":"5_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net (2021), https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Fayyaz, M., et al.: Adaptive token sampling for efficient vision transformers. 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, October 23-27, 2022, Proceedings, Part XI. LNCS, vol. 13671, pp. 396\u2013414. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_24","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., Fei-Fei, L.: Fine-grained car detection for visual census estimation. In: Singh, S., Markovitch, S. (eds.) Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA, pp. 4502\u20134508. AAAI Press (2017). https:\/\/doi.org\/10.1609\/AAAI.V31I1.11174","DOI":"10.1609\/AAAI.V31I1.11174"},{"key":"5_CR11","doi-asserted-by":"publisher","unstructured":"Han, C., et al.: E$$ ^{\\text{2}}$$vpt: an effective and efficient approach for visual prompt tuning. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 17445\u201317456. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01604","DOI":"10.1109\/ICCV51070.2023.01604"},{"key":"5_CR12","unstructured":"Hao, T., Chen, H., Guo, Y., Ding, G.: Consolidator: Mergable adapter with group connections for visual adaptation. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=J_Cja7cpgW"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp. 15979\u201315988. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR14","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"5_CR15","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Schmidt, L., Hajishirzi, H., Farhadi, A.: Editing models with task arithmetic. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=6t0Kwf8-jrj"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Jia, M., et al.: Visual prompt tuning. 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, October 23-27, 2022, Proceedings, Part XXXIII. LNCS, vol. 13693, pp. 709\u2013727. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"5_CR17","doi-asserted-by":"publisher","unstructured":"Jie, S., Deng, Z.: Fact: factor-tuning for lightweight adaptation on vision transformer. In: Williams, B., Chen, Y., Neville, J. (eds.) Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023, pp. 1060\u20131068. AAAI Press (2023). https:\/\/doi.org\/10.1609\/AAAI.V37I1.25187","DOI":"10.1609\/AAAI.V37I1.25187"},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Jie, S., Tang, Y., Ding, N., Deng, Z., Han, K., Wang, Y.: Memory-space visual prompting for efficient vision-language fine-tuning. CoRR abs\/2405.05615 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2405.05615","DOI":"10.48550\/ARXIV.2405.05615"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Jie, S., Wang, H., Deng, Z.: Revisiting the parameter efficiency of adapters from the perspective of precision redundancy. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 17171\u201317180. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01579","DOI":"10.1109\/ICCV51070.2023.01579"},{"key":"5_CR20","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Fei-Fei, L.: Novel dataset for fine-grained image categorization: Stanford dogs (2012)"},{"key":"5_CR21","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)"},{"key":"5_CR22","doi-asserted-by":"publisher","unstructured":"Li, Y., Mao, H., Girshick, R.B., He, K.: Exploring plain vision transformer backbones for object detection. 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, October 23-27, 2022, Proceedings, Part IX. LNCS, vol. 13669, pp. 280\u2013296. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"5_CR23","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: A new baseline for efficient model tuning. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022 (2022). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/00bb4e415ef117f2dee2fc3b778d806d-Abstract-Conference.html"},{"key":"5_CR24","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Evit: Expediting vision transformers via token reorganizations. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=BjyvwnXXVn_"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Lin, M., Chen, M., Zhang, Y., Shen, C., Ji, R., Cao, L.: Super vision transformer. Int. J. Comput. Vis. 131(12), 3136\u20133151 (2023)","DOI":"10.1007\/s11263-023-01861-3"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Lin, Y., Zhang, T., Sun, P., Li, Z., Zhou, S.: Fq-vit: Post-training quantization for fully quantized vision transformer. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, pp. 1173\u20131179. ijcai.org (2022). https:\/\/doi.org\/10.24963\/IJCAI.2022\/164","DOI":"10.24963\/IJCAI.2022\/164"},{"key":"5_CR27","unstructured":"Liu, S., Liu, Z., Cheng, K.: Oscillation-free quantization for low-bit vision transformers. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 21813\u201321824. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/liu23w.html"},{"key":"5_CR28","unstructured":"Liu, Z., Wang, Y., Han, K., Zhang, W., Ma, S., Gao, W.: Post-training quantization for vision transformer. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. pp. 28092\u201328103 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/ec8956637a99787bd197eacd77acce5e-Abstract.html"},{"key":"5_CR29","doi-asserted-by":"publisher","unstructured":"Luo, S., et al.: Lcm-lora: a universal stable-diffusion acceleration module. ArXiv preprint arxiv:2311.05556 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2311.05556","DOI":"10.48550\/ARXIV.2311.05556"},{"key":"5_CR30","doi-asserted-by":"publisher","unstructured":"Marin, D., Chang, J.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers for image classification. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2-7, 2023, pp. 12\u201321. IEEE (2023). https:\/\/doi.org\/10.1109\/WACV56688.2023.00010","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"5_CR31","doi-asserted-by":"publisher","unstructured":"Nilsback, M., Zisserman, A.: Automated flower classification over a large number of classes. In: Sixth Indian Conference on Computer Vision, Graphics & Image Processing, ICVGIP 2008, Bhubaneswar, India, 16-19 December 2008, pp. 722\u2013729. IEEE Computer Society (2008). https:\/\/doi.org\/10.1109\/ICVGIP.2008.47","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"5_CR32","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.: Dynamicvit: Efficient vision transformers with dynamic token sparsification. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 13937\u201313949 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/747d3443e319a22747fbb873e8b2f9f2-Abstract.html"},{"key":"5_CR33","unstructured":"Rebuffi, S., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. In: Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA pp. 506\u2013516 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/e7b24b112a44fdd9ee93bdf998c6ca0e-Abstract.html"},{"key":"5_CR34","doi-asserted-by":"publisher","unstructured":"Shah, V., et al.: Ziplora: any subject in any style by effectively merging loras. ArXiv preprint arxiv:2311.13600 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2311.13600","DOI":"10.48550\/ARXIV.2311.13600"},{"key":"5_CR35","doi-asserted-by":"publisher","unstructured":"Shi, D., Tao, C., Rao, A., Yang, Z., Yuan, C., Wang, J.: Crossget: cross-guided ensemble of tokens for accelerating vision-language transformers. ArXiv preprint arxiv:2305.17455 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2305.17455","DOI":"10.48550\/ARXIV.2305.17455"},{"key":"5_CR36","doi-asserted-by":"publisher","unstructured":"Strudel, R., Pinel, R.G., Laptev, I., Schmid, C.: Segmenter: Transformer for semantic segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp. 7242\u20137252. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00717","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"5_CR37","doi-asserted-by":"publisher","unstructured":"Tang, Y., et al.: Patch slimming for efficient vision transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp. 12155\u201312164. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01185","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"5_CR38","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 10347\u201310357. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"5_CR39","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"5_CR40","doi-asserted-by":"publisher","unstructured":"Wei, S., Ye, T., Zhang, S., Tang, Y., Liang, J.: Joint token pruning and squeezing towards more aggressive compression of vision transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pp. 2092\u20132101. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00208","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"5_CR41","doi-asserted-by":"publisher","unstructured":"Wu, X., Zeng, F., Wang, X., Wang, Y., Chen, X.: PPT: token pruning and pooling for efficient vision transformers. ArXiv preprint arxiv:2310.01812 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.01812","DOI":"10.48550\/ARXIV.2310.01812"},{"key":"5_CR42","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: Evo-vit: slow-fast token evolution for dynamic vision transformer. In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pp. 2964\u20132972. AAAI Press (2022). https:\/\/doi.org\/10.1609\/AAAI.V36I3.20202","DOI":"10.1609\/AAAI.V36I3.20202"},{"key":"5_CR43","doi-asserted-by":"publisher","unstructured":"Yin, H., Vahdat, A., \u00c1lvarez, J.M., Mallya, A., Kautz, J., Molchanov, P.: A-vit: Adaptive tokens for efficient vision transformer. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp. 10799\u201310808. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01054","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"5_CR44","unstructured":"Yoo, S., Kim, E., Jung, D., Lee, J., Yoon, S.: Improving visual prompt tuning for self-supervised vision transformers. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 40075\u201340092. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/yoo23a.html"},{"key":"5_CR45","doi-asserted-by":"publisher","unstructured":"Yu, L., Xiang, W.: X-pruner: explainable pruning for vision transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pp. 24355\u201324363. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02333","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"5_CR46","doi-asserted-by":"publisher","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pp.\u00a01\u20139. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/V1\/2022.ACL-SHORT.1","DOI":"10.18653\/V1\/2022.ACL-SHORT.1"},{"key":"5_CR47","unstructured":"Zhai, X., et al.: The visual task adaptation benchmark. ArXiv preprint arxiv:1910.04867 (2019)"},{"key":"5_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1007\/978-3-030-58580-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JO Zhang","year":"2020","unstructured":"Zhang, J.O., Sax, A., Zamir, A., Guibas, L., Malik, J.: Side-tuning: a baseline for network adaptation via additive side networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 698\u2013714. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_41"},{"key":"5_CR49","unstructured":"Zhang, J., Chen, S., Liu, J., He, J.: Composing parameter-efficient modules with arithmetic operation. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023 (2023). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/299a08ee712d4752c890938da99a77c6-Abstract-Conference.html"}],"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\/978-3-031-72640-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:38:03Z","timestamp":1730108283000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}