{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:40:11Z","timestamp":1780501211734,"version":"3.54.1"},"publisher-location":"Cham","reference-count":104,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727832","type":"print"},{"value":"9783031727849","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72784-9_5","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"75-95","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["SHERL: Synthesizing High Accuracy and\u00a0Efficient Memory for\u00a0Resource-Limited Transfer Learning"],"prefix":"10.1007","author":[{"given":"Haiwen","family":"Diao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"5_CR1","unstructured":"Alayrac, J., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Bapna, A., Firat, O.: Simple, scalable adaptation for neural machine translation. In: EMNLP, pp. 1538\u20131548 (2019)","DOI":"10.18653\/v1\/N19-1191"},{"key":"5_CR3","unstructured":"Bentivogli, L., Magnini, B., Dagan, I., Dang, H.T., Giampiccolo, D.: The fifth PASCAL recognizing textual entailment challenge. In: TAC (2009)"},{"key":"5_CR4","unstructured":"Cai, H., Gan, C., Zhu, L., Han, S.: TinyTL: reduce memory, not parameters for efficient on-device learning. In: NeurIPS (2020)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cer, D.M., Diab, M.T., Agirre, E., Lopez-Gazpio, I., Specia, L.: SemEval-2017 Task 1: semantic textual similarity - multilingual and cross-lingual focused evaluation. arXiv arXiv:1708.00055 (2017)","DOI":"10.18653\/v1\/S17-2001"},{"key":"5_CR6","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL, pp. 190\u2013200 (2011)"},{"key":"5_CR7","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., Zhang, K.: PLOT: prompt learning with optimal transport for vision-language models. In: ICLR (2023)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., Wang, C.: Learning the best pooling strategy for visual semantic embedding. In: CVPR, pp. 15789\u201315798 (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Ma, W., Xiao, J., Zhang, H., Chang, S.F.: Ref-NMS: breaking proposal bottlenecks in two-stage referring expression grounding. In: AAAI, vol.\u00a035, pp. 1036\u20131044 (2021)","DOI":"10.1609\/aaai.v35i2.16188"},{"issue":"11","key":"5_CR10","doi-asserted-by":"crossref","first-page":"13218","DOI":"10.1109\/TPAMI.2023.3289667","volume":"45","author":"L Chen","year":"2023","unstructured":"Chen, L., Zheng, Y., Niu, Y., Zhang, H., Xiao, J.: Counterfactual samples synthesizing and training for robust visual question answering. IEEE TPAMI 45(11), 13218\u201313234 (2023)","journal-title":"IEEE TPAMI"},{"key":"5_CR11","unstructured":"Chen, S., et al.: AdaptFormer: adapting vision transformers for scalable visual recognition. In: NeurIPS (2022)"},{"key":"5_CR12","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv arXiv:1604.06174 (2016)"},{"key":"5_CR13","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML, vol.\u00a0119, pp. 1597\u20131607 (2020)"},{"key":"5_CR14","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. In: ICLR (2023)"},{"key":"5_CR15","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLoRA: efficient finetuning of quantized LLMs. arXiv arXiv:2305.14314 (2023)"},{"key":"5_CR16","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)"},{"key":"5_CR17","unstructured":"Diao, H., Cui, Y., Li, X., Wang, Y., Lu, H., Wang, X.: Unveiling encoder-free vision-language models. arXiv arXiv:2406.11832 (2024)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Diao, H., Wan, B., Zhang, Y., Jia, X., Lu, H., Chen, L.: UniPT: universal parallel tuning for transfer learning with efficient parameter and memory. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02714"},{"key":"5_CR19","first-page":"3341","volume":"33","author":"H Diao","year":"2024","unstructured":"Diao, H., Zhang, Y., Gao, S., Ruan, X., Lu, H.: Deep boosting learning: a brand-new cooperative approach for image-text matching. IEEE TIP 33, 3341\u20133352 (2024)","journal-title":"IEEE TIP"},{"key":"5_CR20","first-page":"2322","volume":"32","author":"H Diao","year":"2023","unstructured":"Diao, H., Zhang, Y., Liu, W., Ruan, X., Lu, H.: Plug-and-play regulators for image-text matching. IEEE TIP 32, 2322\u20132334 (2023)","journal-title":"IEEE TIP"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: AAAI, pp. 1218\u20131226 (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"5_CR22","unstructured":"Dolan, W.B., Brockett, C.: Automatically constructing a corpus of sentential paraphrases. In: IWP (2005)"},{"key":"5_CR23","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"5_CR24","unstructured":"Dukler, Y., et al.: Your representations are in the network: composable and parallel adaptation for large scale models. In: NeurIPS (2023)"},{"key":"5_CR25","unstructured":"Evci, U., Dumoulin, V., Larochelle, H., Mozer, M.C.: Head2Toe: utilizing intermediate representations for better transfer learning. In: ICML, vol.\u00a0162, pp. 6009\u20136033 (2022)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: EVA: exploring the limits of masked visual representation learning at scale. In: CVPR, pp. 19358\u201319369 (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"5_CR27","unstructured":"Gao, P., et al.: CLIP-adapter: better vision-language models with feature adapters. arXiv arXiv:2110.04544 (2021)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind one embedding space to bind them all. In: CVPR, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"5_CR29","unstructured":"Gomez, A.N., Ren, M., Urtasun, R., Grosse, R.B.: The reversible residual network: backpropagation without storing activations. In: NeurIPS, pp. 2214\u20132224 (2017)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR, pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Gu, Y., Han, X., Liu, Z., Huang, M.: PPT: pre-trained prompt tuning for few-shot learning. In: ACL, pp. 8410\u20138423 (2022)","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Guo, D., Rush, A.M., Kim, Y.: Parameter-efficient transfer learning with diff pruning. In: ACL, pp. 4884\u20134896 (2021)","DOI":"10.18653\/v1\/2021.acl-long.378"},{"key":"5_CR33","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. In: ICLR (2022)"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 15979\u201315988 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR37","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: ICML, Proceedings of Machine Learning Research, vol.\u00a097, pp. 2790\u20132799 (2019)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: ACL, pp. 328\u2013339 (2018)","DOI":"10.18653\/v1\/P18-1031"},{"key":"5_CR39","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Hu, Z., Li, Y., Lyu, M.R., Wang, L.: VL-PET: vision-and-language parameter-efficient tuning via granularity control. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00281"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: VoP: text-video co-operative prompt tuning for cross-modal retrieval. In: CVPR, pp. 6565\u20136574 (2023)","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: CVPR, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"5_CR43","unstructured":"Iyer, S., Dandekar, N., Csernai, K., et\u00a0al.: First quora dataset release: question pairs. data. quora.com (2017)"},{"key":"5_CR44","doi-asserted-by":"publisher","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"5_CR45","unstructured":"Jiang, Z., et al.: Res-Tuning: a flexible and efficient tuning paradigm via unbinding tuner from backbone. In: NeurIPS (2023)"},{"key":"5_CR46","unstructured":"Jie, S., Deng, Z.: Convolutional bypasses are better vision transformer adapters. arXiv arXiv:arXiv:2207.07039 (2022)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Jie, S., Deng, Z.: FacT: factor-tuning for lightweight adaptation on vision transformer. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"5_CR48","doi-asserted-by":"publisher","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13695, pp. 105\u2013124 (2022). Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-19833-5_7","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: ICCV, pp. 1760\u20131770 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H.A., Maaz, M., Khan, S., Khan, F.S.: MaPLe: multi-modal prompt learning. arXiv arXiv:2210.03117 (2022)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"5_CR51","unstructured":"Kim, K., Laskin, M., Mordatch, I., Pathak, D.: How to adapt your large-scale vision-and-language model. OpenReview (2021)"},{"key":"5_CR52","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: The efficient transformer. In: ICLR (2020)"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: EMNLP, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"5_CR54","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML, vol.\u00a0202, pp. 19730\u201319742 (2023)"},{"key":"5_CR55","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICLR, vol.\u00a0162, pp. 12888\u201312900 (2022)"},{"key":"5_CR56","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: ACL, pp. 4582\u20134597 (2021)"},{"key":"5_CR57","unstructured":"Lialin, V., Shivagunde, N., Muckatira, S., Rumshisky, A.: Stack more layers differently: high-rank training through low-rank updates. arXiv arXiv:2307.05695 (2023)"},{"key":"5_CR58","unstructured":"Lian, D., Zhou, D., Feng, J., Wang, X.: Scaling & shifting your features: a new baseline for efficient model tuning. In: NeurIPS (2022)"},{"key":"5_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"5_CR60","unstructured":"Liu, H., et al.: Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. arXiv arXiv:2205.05638 (2022)"},{"key":"5_CR61","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv arXiv:1907.11692 (2019)"},{"key":"5_CR62","doi-asserted-by":"crossref","unstructured":"Liu, Y., An, C., Qiu, X.: Y-Tuning: an efficient tuning paradigm for large-scale pre-trained models via label representation learning. arXiv arXiv:2202.09817 (2022)","DOI":"10.1007\/s11704-023-3131-8"},{"key":"5_CR63","unstructured":"Lu, H., et al.: UniAdapter: unified parameter-efficient transfer learning for cross-modal modeling. arXiv arXiv:2302.06605 (2023)"},{"key":"5_CR64","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS (2022)"},{"key":"5_CR65","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of CLIP for end to end video clip retrieval. arXiv arXiv:2104.08860 (2021)","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"5_CR66","unstructured":"Mahabadi, R.K., Henderson, J., Ruder, S.: Compacter: efficient low-rank hypercomplex adapter layers. In: NeurIPS, pp. 1022\u20131035 (2021)"},{"key":"5_CR67","unstructured":"Mahabadi, R.K., Ruder, S., Dehghani, M., Henderson, J.: Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. In: ACL, pp. 565\u2013576 (2021)"},{"key":"5_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-030-01216-8_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Mahajan","year":"2018","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12"},{"key":"5_CR69","doi-asserted-by":"crossref","unstructured":"Mangalam, K., et al.: Reversible vision transformers. In: CVPR, pp. 10820\u201310830 (2022)","DOI":"10.1109\/CVPR52688.2022.01056"},{"key":"5_CR70","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"5_CR71","unstructured":"Micikevicius, P., et al.: Mixed precision training. arXiv arXiv:1710.03740 (2017)"},{"key":"5_CR72","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. In: EACL, pp. 487\u2013503 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"5_CR73","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Yu, Z., Wu, Q.: VLN-PETL: parameter-efficient transfer learning for vision-and-language navigation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01416"},{"key":"5_CR74","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"key":"5_CR75","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)"},{"key":"5_CR76","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21, 140:1\u2013140:67 (2020)"},{"key":"5_CR77","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020, Virtual Event\/Atlanta, Georgia, USA, 9\u201319 November 2020, p.\u00a020 (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"5_CR78","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: EMNLP, pp. 2383\u20132392 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"5_CR79","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: CVPR, pp. 18061\u201318070 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"5_CR80","unstructured":"Shen, S., et al.: How much can CLIP benefit vision-and-language tasks? In: ICLR (2022)"},{"key":"5_CR81","doi-asserted-by":"crossref","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP, pp. 1631\u20131642 (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"5_CR82","unstructured":"Sun, Q., et al.: Generative pretraining in multimodality. arXiv arXiv:2307.05222 (2023)"},{"key":"5_CR83","unstructured":"Sung, Y., Cho, J., Bansal, M.: LST: ladder side-tuning for parameter and memory efficient transfer learning. In: NeurIPS (2022)"},{"key":"5_CR84","doi-asserted-by":"crossref","unstructured":"Sung, Y., Cho, J., Bansal, M.: VL-ADAPTER: parameter-efficient transfer learning for vision-and-language tasks. In: CVPR, pp. 5217\u20135227 (2022)","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"5_CR85","unstructured":"Sung, Y., Nair, V., Raffel, C.: Training neural networks with fixed sparse masks. In: NeurIPS, pp. 24193\u201324205 (2021)"},{"key":"5_CR86","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv arXiv:2302.13971 (2023)"},{"key":"5_CR87","unstructured":"Tsimpoukelli, M., Menick, J., Cabi, S., Eslami, S.M.A., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. In: NeurIPS, pp. 200\u2013212 (2021)"},{"key":"5_CR88","doi-asserted-by":"crossref","unstructured":"Tu, C., Mai, Z., Chao, W.: Visual query tuning: towards effective usage of intermediate representations for parameter and memory efficient transfer learning. In: CVPR, pp. 7725\u20137735 (2023)","DOI":"10.1109\/CVPR52729.2023.00746"},{"key":"5_CR89","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: ICLR (2019)","DOI":"10.18653\/v1\/W18-5446"},{"key":"5_CR90","unstructured":"Wang, N., Choi, J., Brand, D., Chen, C., Gopalakrishnan, K.: Training deep neural networks with 8-bit floating point numbers. In: NeurIPS, pp. 7686\u20137695 (2018)"},{"key":"5_CR91","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Image as a foreign language: BEiT pretraining for all vision and vision-language tasks. arXiv arXiv:2208.10442 (2022)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"5_CR92","doi-asserted-by":"crossref","unstructured":"Warstadt, A., Singh, A., Bowman, S.R.: Neural network acceptability judgments. In: TACL, vol. 7, pp. 625\u2013641 (2019)","DOI":"10.1162\/tacl_a_00290"},{"key":"5_CR93","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. In: NAACL, pp. 1112\u20131122 (2018)","DOI":"10.18653\/v1\/N18-1101"},{"key":"5_CR94","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 5987\u20135995 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"5_CR95","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"5_CR96","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. In: TACL, vol. 2, pp. 67\u201378 (2014)","DOI":"10.1162\/tacl_a_00166"},{"key":"5_CR97","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"5_CR98","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: ACL, pp.\u00a01\u20139 (2022)"},{"key":"5_CR99","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_CR100","unstructured":"Zhang, Q., et al.: Adaptive budget allocation for parameter-efficient fine-tuning. In: ICLR (2023)"},{"key":"5_CR101","unstructured":"Zhang, Y., et al.: Meta-transformer: a unified framework for multimodal learning. arXiv arXiv:2307.10802 (2023)"},{"key":"5_CR102","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models. arXiv arXiv:2302.00923 (2023)"},{"key":"5_CR103","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16795\u201316804 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"5_CR104","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. IJCV 130(9), 2337\u20132348 (2022). https:\/\/doi.org\/10.1007\/s11263-022-01653-1","journal-title":"IJCV"}],"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\/978-3-031-72784-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:22:59Z","timestamp":1732828979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72784-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727832","9783031727849"],"references-count":104,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72784-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}