{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:28:40Z","timestamp":1772908120413,"version":"3.50.1"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1937500"],"award-info":[{"award-number":["CCF-1937500"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.00024","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"139-149","source":"Crossref","is-referenced-by-count":563,"title":["Learning to Prompt for Continual Learning"],"prefix":"10.1109","author":[{"given":"Zifeng","family":"Wang","sequence":"first","affiliation":[{"name":"Northeastern University"}]},{"given":"Zizhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Cloud AI"}]},{"given":"Chen-Yu","family":"Lee","sequence":"additional","affiliation":[{"name":"Google Cloud AI"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Ruoxi","family":"Sun","sequence":"additional","affiliation":[{"name":"Google Cloud AI"}]},{"given":"Xiaoqi","family":"Ren","sequence":"additional","affiliation":[{"name":"Google Cloud AI"}]},{"given":"Guolong","family":"Su","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Vincent","family":"Perot","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Jennifer","family":"Dy","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Tomas","family":"Pfister","sequence":"additional","affiliation":[{"name":"Google Cloud AI"}]}],"member":"263","reference":[{"key":"ref39","article-title":"An empirical investigation of the role of pre-training in lifelong learning","author":"mehta","year":"0","journal-title":"ICML Workshop on Theory and Foundation of Continual Learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"ref33","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"Gradient episodic memory for continual learning","author":"lopez-paz","year":"2017","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Gen-eralized variational continual learning","author":"loo","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"Core50: a new dataset and benchmark for continuous object recognition","author":"lomonaco","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic inter-ference in connectionist networks: The sequential learning problem","volume":"24","author":"mccloskey","year":"1989","journal-title":"Psychology of Learning and Motivation"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.102.3.419"},{"key":"ref35","article-title":"Packnet: Adding mul-tiple tasks to a single network by iterative pruning","author":"mallya","year":"2018","journal-title":"CVPR"},{"key":"ref34","article-title":"Online continual learning in image classification: An empirical survey","author":"mai","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref60","first-page":"15173","article-title":"Supermasks in superposition","volume":"33","author":"wortsman","year":"2020","journal-title":"NeurIPS"},{"key":"ref62","article-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref64","article-title":"Lifelong learning with dynamically expandable net-works","author":"yoon","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref65","article-title":"Contin-ual learning through synaptic intelligence","author":"zenke","year":"2017","journal-title":"ICML"},{"key":"ref66","article-title":"Task agnostic continual learning using online variational bayes","author":"zeno","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in nat-ural language processing","author":"liu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref67","article-title":"Nested hierarchical trans-former: Towards accurate, data-efficient and interpretable vi-sual understanding","author":"zhang","year":"2022","journal-title":"AAAI"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.02.001"},{"key":"ref2","author":"bulatov","year":"2011","journal-title":"The notMNIST dataset"},{"key":"ref1","article-title":"Memory aware synapses: Learning what (not) to forget","author":"aljundi","year":"2018","journal-title":"ECCV"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref22","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neu-ral networks","volume":"114","author":"kirkpatrick","year":"2017","journal-title":"PNAS"},{"key":"ref24","author":"lecun","year":"1998","journal-title":"The MNIST Database of Handwritten Digits"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2016.05.004"},{"key":"ref26","first-page":"3925","article-title":"Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting","author":"li","year":"2019","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref50","article-title":"Progressive neural networks","author":"rusu","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref51","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","author":"serra","year":"0","journal-title":"ICML"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00073"},{"key":"ref58","article-title":"K-adapter: Infusing knowledge into pre-trained models with adapters","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref57","article-title":"Efficient continual learning with modular networks and task-driven priors","author":"veniat","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref56","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref55","article-title":"Three scenar-ios for continual learning","author":"van de ven","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref54","article-title":"Privacy-preserving deep learning","author":"shokri","year":"0","journal-title":"Proc SIGSAC conference on computer and communications security"},{"key":"ref53","article-title":"Eric Wallace, and Sameer Singh. Autoprompt: Eliciting knowl-edge from language models with automatically generated prompts","author":"shin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref52","article-title":"Encoders and ensembles for task-free continual learning","author":"shanahan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"An image is worth 16x16 words: Trans-formers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLR OpenReview net"},{"key":"ref40","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_23"},{"key":"ref13","article-title":"Towards ro-bust evaluations of continual learning","author":"farquhar","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.09.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793982"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"hu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Continual learning of a mixed sequence of similar and dissimilar tasks","volume":"33","author":"ke","year":"2020","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Co21: Contrastive continual learning","author":"cha","year":"2021","journal-title":"ICCV"},{"key":"ref3","article-title":"Dark experience for general continual learning: a strong, simple baseline","author":"buzzega","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Using hindsight to an-chor past knowledge in continual learning","volume":"2","author":"chaudhry","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref5","first-page":"532","article-title":"Riemannian walk for incremen-tal learning: Understanding forgetting and intransigence","author":"chaudhry","year":"2018","journal-title":"ECCV"},{"key":"ref8","article-title":"On tiny episodic memo-ries in continual learning","author":"chaudhry","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Efficient lifelong learning with a-gem","author":"chaudhry","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref46","article-title":"Gdumb: A simple approach that questions our progress in continual learning","author":"prabhu","year":"2020","journal-title":"ECCV"},{"key":"ref45","article-title":"Contextual transformation networks for online continual learning","author":"pham","year":"2020","journal-title":"ICLRE"},{"key":"ref48","article-title":"Continual unsuper-vised representation learning","volume":"32","author":"rao","year":"2019","journal-title":"NeurIPS"},{"key":"ref47","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"JMLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref41","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref44","article-title":"Dualnet: Continual learning, fast and slow","author":"pham","year":"2021","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Adapterfusion: Non-destructive task composition for transfer learning","author":"pfeiffer","year":"2020","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09878681.pdf?arnumber=9878681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:52:23Z","timestamp":1665780743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9878681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.00024","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}