{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:21:16Z","timestamp":1740133276654,"version":"3.37.3"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122013","U2001211"],"award-info":[{"award-number":["62122013","U2001211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Innovative Development Joint Fund Key Projects of Shandong NSF","doi-asserted-by":"publisher","award":["ZR2022LZH007"],"award-info":[{"award-number":["ZR2022LZH007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3445731","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T18:07:58Z","timestamp":1724436478000},"page":"5577-5592","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Generate Parameters of ConvNets for Unseen Image Data"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8973-0231","authenticated-orcid":false,"given":"Shiye","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8746-6900","authenticated-orcid":false,"given":"Kaituo","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9789-7632","authenticated-orcid":false,"given":"Changsheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0247-9866","authenticated-orcid":false,"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-8379","authenticated-orcid":false,"given":"Guoren","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kendall"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"ref3","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2877359"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"ref10","article-title":"Scalable second order optimization for deep learning","volume-title":"arXiv:2002.09018","author":"Anil","year":"2020"},{"key":"ref11","first-page":"1","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref12","article-title":"Layer normalization","volume-title":"arXiv:1607.06450","author":"Ba","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303957"},{"key":"ref14","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","volume-title":"arXiv:1708.07747","author":"Xiao","year":"2017"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref15"},{"key":"ref16","first-page":"1","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref17","first-page":"81","article-title":"Canonical correlation analysis","volume-title":"Proc. Inst. Phonetic Sci. Univ. Amsterdam","volume":"25","author":"Weenink"},{"key":"ref18","first-page":"1","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ha"},{"key":"ref19","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref20","article-title":"Bayesian hypernetworks","volume-title":"arXiv:1710.04759","author":"Krueger","year":"2017"},{"key":"ref21","first-page":"1","article-title":"Graph hypernetworks for neural architecture search","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref22","first-page":"1","article-title":"Continual learning with hypernetworks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"von Oswald"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_36"},{"key":"ref24","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamsian"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00883"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01110"},{"key":"ref27","first-page":"18490","article-title":"Hyper-Style: StyleGAN inversion with HyperNetworks for real image editing","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Alaluf"},{"key":"ref28","first-page":"565","article-title":"Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Mahabadi"},{"key":"ref29","first-page":"36889","article-title":"Polyhistor: Parameter-efficient multi-task adaptation for dense vision tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref30","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref31","first-page":"29433","article-title":"Parameter prediction for unseen deep architectures","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Knyazev"},{"key":"ref32","first-page":"27075","article-title":"Hypertransformer: Model generation for supervised and semi-supervised few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhmoginov"},{"issue":"7","key":"ref33","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"volume-title":"Divide the gradient by a running average of its recent magnitude. Coursera: Neural networks for machine learning","year":"2017","author":"Tieleman","key":"ref35"},{"key":"ref36","first-page":"1","article-title":"How does batch normalization help optimization?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Santurkar"},{"key":"ref37","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. USENIX Symp. Netw. Syst. Design Implement.","author":"Sapio"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref39","article-title":"Automated relational meta-learning","volume-title":"arXiv:2001.00745","author":"Yao","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref41","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref42","first-page":"2554","article-title":"Meta networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"key":"ref43","first-page":"10177","article-title":"Subspace learning for effective meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.368"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487623"},{"key":"ref49","first-page":"1","article-title":"Subset selection by Pareto optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Qian"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0709640104"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.32388\/li2ajv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref53","first-page":"1","article-title":"Tadam: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Oreshkin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20584"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref56","article-title":"Adjusting for bias with procedural data","volume-title":"arXiv:2204.01108","author":"Gupta","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00820"},{"key":"ref59","first-page":"1179","article-title":"Single layer predictive normalized maximum likelihood for out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bibas"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00702"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00872"},{"key":"ref62","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","volume-title":"arXiv:1910.04867","author":"Zhai","year":"2019"},{"key":"ref63","first-page":"1","article-title":"Meta-learning via hypernetworks","volume-title":"Proc. Workshop Meta-Learn. NeurIPS","author":"Zhao"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01543"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00223"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref67","first-page":"20320","article-title":"Noise2Same: Optimizing a self-supervised bound for image denoising","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"article-title":"The Caltech-UCSD Birds-200\u20132011 dataset","year":"2011","author":"Wah","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.161"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref72","article-title":"LLaMA: Open and efficient foundation language models","volume-title":"arXiv:2302.13971","author":"Touvron","year":"2023"},{"key":"ref73","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"arXiv:2304.10592","author":"Zhu","year":"2023"},{"key":"ref74","article-title":"Vision transformer adapter for dense predictions","volume-title":"arXiv:2205.08534","author":"Chen","year":"2022"},{"key":"ref75","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"arXiv:2106.09685","author":"Hu","year":"2021"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10645765.pdf?arnumber=10645765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T17:31:40Z","timestamp":1728581500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3445731","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2024]]}}}