{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:12Z","timestamp":1778048352560,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00243","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2465-2474","source":"Crossref","is-referenced-by-count":0,"title":["PVeRA: Probabilistic Vector-Based Random Matrix Adaptation"],"prefix":"10.1109","author":[{"given":"Leo","family":"Fillioux","sequence":"first","affiliation":[{"name":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enzo","family":"Ferrante","sequence":"additional","affiliation":[{"name":"Universidad de Buenos Aires,Institute of Computer Sciences, CONICET"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul-Henry","family":"Courn\u00e8de","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Vakalopoulou","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stergios","family":"Christodoulidis","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref2","author":"Bahdanau","year":"2016","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref3","article-title":"Deepmind lab","author":"Beattie","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0438"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref6","author":"Chen","year":"2020","journal-title":"A simple framework for contrastive learning of visual representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095889"},{"key":"ref11","author":"Gal","year":"2016","journal-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref13","author":"Guo","year":"2017","journal-title":"On calibration of modern neural networks"},{"key":"ref14","article-title":"Smt: Fine-tuning large language models with sparse matrices","volume-title":"International Conference on Learning Representations","author":"He"},{"key":"ref15","author":"He","year":"2023","journal-title":"Deber-tav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref17","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Houlsby"},{"key":"ref18","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref21","year":"2015","journal-title":"Kaggle diabetic retinopathy detection"},{"key":"ref22","article-title":"Auto-Encoding Variational Bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings","author":"Kingma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","article-title":"VeRA: Vector-based random matrix adaptation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kopiczko"},{"key":"ref25","article-title":"Learning multiple layers of features from tiny images","volume-title":"Technical report","author":"Krizhevsky","year":"2009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref29","author":"Liu","year":"2022","journal-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning"},{"key":"ref30","article-title":"Dora: Weight-decomposed low-rank adaptation","author":"Liu","year":"2024"},{"key":"ref31","author":"Loshchilov","year":"2019","journal-title":"Decoupled weight decay regularization"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref33","author":"Mahabadi","year":"2021","journal-title":"Compacter: Efficient low-rank hypercomplex adapter layers"},{"key":"ref34","volume-title":"dsprites: Disentanglement testing sprites dataset","author":"Matthey","year":"2017"},{"key":"ref35","author":"Mukhoti","year":"2020","journal-title":"Calibrating deep neural networks using focal loss"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0745-0","volume-title":"Bayesian Learning for Neural Networks","author":"Neal","year":"1996"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref40","article-title":"Modeling uncertainty with hedged instance embedding","author":"Oh","year":"2018"},{"key":"ref41","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref43","article-title":"Probabilistic outputs for support vector machines and comparison to regularized likelihood methods","author":"Platt","year":"1999","journal-title":"Advances in Large Margin Classifiers"},{"key":"ref44","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00700"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00182"},{"key":"ref47","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_24"},{"key":"ref49","author":"Wang","year":"2019","journal-title":"Glue: A multi-task benchmark and analysis platform for natural language understanding"},{"key":"ref50","first-page":"36","article-title":"Universality and limitations of prompt tuning","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref53","author":"Yosinski","year":"2014","journal-title":"How transferable are features in deep neural networks?"},{"key":"ref54","first-page":"609","article-title":"Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williams College, Williamstown, MA, USA, June 28 - July 1, 2001","author":"Zadrozny"},{"key":"ref55","author":"Zhai","year":"2020","journal-title":"A large-scale study of representation learning with the visual task adaptation benchmark"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492664.pdf?arnumber=11492664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:59:06Z","timestamp":1778047146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00243","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}