{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:12:33Z","timestamp":1782385953148,"version":"3.54.5"},"reference-count":120,"publisher":"American Association for the Advancement of Science (AAAS)","content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Intell Comput"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Active learning (AL) is an effective sample selection approach that annotates only a subset of the training data to address the challenge of data annotation, and deep learning (DL) is data-intensive and reliant on abundant training data. Deep active learning (DeepAL) benefits from the integration of AL and DL, offering an efficient solution that balances model performance and annotation costs. The importance of DeepAL has been increasingly recognized with the emergence of large foundation models that depend heavily on substantial computational resources and extensive training data. This survey endeavors to provide a comprehensive overview of DeepAL. Specifically, we first analyze and summarize various sample query strategies, data querying considerations, model training paradigms, and real-world applications of DeepAL. In addition, we discuss the challenges that arise in the era of foundation models and propose potential directions for future AL research. The survey aims to bridge a gap in the existing literature by organizing and summarizing current approaches, offering insights into DeepAL and highlighting the necessity of developing specialized DeepAL techniques tailored to foundation models. By critically examining the current state of DeepAL, this survey contributes to a more profound understanding of the field and serves as a guide for researchers and practitioners interested in DeepAL techniques.<\/jats:p>","DOI":"10.34133\/icomputing.0058","type":"journal-article","created":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T08:14:03Z","timestamp":1698999243000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":16,"title":["A Survey of Deep Active Learning for Foundation Models"],"prefix":"10.34133","volume":"2","author":[{"given":"Tianjiao","family":"Wan","sequence":"first","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaimin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China."},{"name":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"issue":"2","key":"e_1_3_2_2_2","first-page":"3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst. 2012;25(2):3065386.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_2_3_2","unstructured":"Vaswani A. Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS 2017); 2017."},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Wang D Cui P Zhu W. Paper presented at: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining (2016) pp. 1225\u20131234.","DOI":"10.1145\/2939672.2939753"},{"issue":"1","key":"e_1_3_2_5_2","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1613\/jair.295","article-title":"Active learning with statistical models","volume":"4","author":"Cohn DA","year":"1996","unstructured":"Cohn DA, Ghahramani Z, Jordan MI. Active learning with statistical models. J Artif Intell Res. 1996;4(1):129\u2013145.","journal-title":"J Artif Intell Res"},{"key":"e_1_3_2_6_2","unstructured":"Sun M. Proceedings of the sixth ACM international conference on Web search and data mining; 2013; Rome Italy."},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Hoi SC Jin R Zhu J Lyu MR. Proceedings of the 23rd International Conference on Machine Learning (2006) pp. 417\u2013424.","DOI":"10.1145\/1143844.1143897"},{"key":"e_1_3_2_8_2","unstructured":"Devlin J Chang M-W Lee K Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv. 2018. https:\/\/doi.org\/10.48550\/arXiv.1810.04805"},{"key":"e_1_3_2_9_2","unstructured":"Wei L Jiang Z Huang W Sun L. Instructiongpt-4: A 200-instruction paradigm for fine-tuning minigpt-4. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2308.12067"},{"key":"e_1_3_2_10_2","unstructured":"Zhou C. Lima: Less is more for alignment. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.11206"},{"issue":"9","key":"e_1_3_2_11_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3472291","article-title":"A survey of deep active learning","volume":"54","author":"Ren P","year":"2021","unstructured":"Ren P, Xiao Y, Chang X, Huang PY, Li Z, Gupta BB, Chen X, Wang X. A survey of deep active learning. ACM Comput Surv (CSUR). 2021;54(9):1, 40.","journal-title":"ACM Comput Surv (CSUR)"},{"key":"e_1_3_2_12_2","unstructured":"Schr\u00f6der C Niekler A. A survey of active learning for text classification using deep neural networks. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2008.07267"},{"issue":"10","key":"e_1_3_2_13_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3510414","article-title":"A survey on active deep learning: From model driven to data driven","volume":"54","author":"Liu P","year":"2022","unstructured":"Liu P, Wang L, Ranjan R, He G, Zhao L. A survey on active deep learning: From model driven to data driven. ACM Comput Surv (CSUR). 2022;54(10s):1.","journal-title":"ACM Comput Surv (CSUR)"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Takezoe R Liu X Mao S Chen MT Feng Z Zhang S Wang X. Deep active learning for computer vision: Past and future. APSIPA Transactions on Signal and Information Processing; 2023.","DOI":"10.1561\/116.00000057"},{"key":"e_1_3_2_15_2","unstructured":"Netzer Y. Reading digits in natural images with unsupervised feature learning; 2011."},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/584091.584093","article-title":"A mathematical theory of communication","volume":"5","author":"Shannon CE","year":"2001","unstructured":"Shannon CE. A mathematical theory of communication. ACM SIGMOBILE Mob ComputCommun Rev. 2001;5:3.","journal-title":"ACM SIGMOBILE Mob ComputCommun Rev"},{"key":"e_1_3_2_17_2","unstructured":"Wang D Shang Y. Paper presented at: International joint conference on neural networks (IJCNN) (IEEE 2014); 2014."},{"key":"e_1_3_2_18_2","unstructured":"Kampffmeyer M Salberg A-B Jenssen R. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition workshops. 2016;1\u20139."},{"key":"e_1_3_2_19_2","unstructured":"Houlsby N Husz\u00e1r F Ghahramani Z Lengyel M. Bayesian active learning for classification and preference learning. arXiv. 2011. https:\/\/doi.org\/10.48550\/arXiv.1112.5745"},{"key":"e_1_3_2_20_2","unstructured":"Gal Y Islam R Ghahramani Z. Paper presented at: International Conference on Machine Learning (PMLR. 2017);1183\u20131192."},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Beluch WH Genewein T N\u00fcrnberger A K\u00f6hler JM. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018;9368\u20139377.","DOI":"10.1109\/CVPR.2018.00976"},{"key":"e_1_3_2_22_2","unstructured":"Kirsch A Van Amersfoort J Gal Y. Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. Paper presented at:Advances in neural information processing systems; 2019 Dec 8; Red Hook NY United States."},{"key":"e_1_3_2_23_2","unstructured":"Smith FB. International Conference on Artificial Intelligence and Statistics (PMLR; 2023). p. 7331\u20137348."},{"issue":"11","key":"e_1_3_2_24_2","doi-asserted-by":"crossref","first-page":"2642","DOI":"10.1109\/TMI.2019.2907805","article-title":"Intelligent labeling based on fisher information for medical image segmentation using deep learning","volume":"38","author":"Sourati J","year":"2019","unstructured":"Sourati J, Gholipour A, Dy JG, Tomas-Fernandez X, Kurugol S, Warfield SK. Intelligent labeling based on fisher information for medical image segmentation using deep learning. IEEE Trans Med Imaging. 2019;38(11):2642\u20132653.","journal-title":"IEEE Trans Med Imaging"},{"key":"e_1_3_2_25_2","first-page":"8566","article-title":"Proceedings of the AAAI conference on","volume":"36","author":"Wang T","year":"2022","unstructured":"Wang T. Proceedings of the AAAI conference on. Artif Intell. 2022;36:8566\u20138574.","journal-title":"Artif Intell"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Sheikh R. Paper presented at: IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 1350\u20131356. 2020.","DOI":"10.1109\/ICRA40945.2020.9196722"},{"key":"e_1_3_2_27_2","unstructured":"Ash JT Zhang C Krishnamurthy A Langford J Agarwal A. Deep batch active learning by diverse uncertain gradient lower bounds. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1906.03671"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Yoo D Kweon IS. Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition. 2019;93\u2013102.","DOI":"10.1109\/CVPR.2019.00018"},{"key":"e_1_3_2_29_2","unstructured":"Huang S Wang T Xiong H Huan J Dou D. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021;3447\u20133456."},{"key":"e_1_3_2_30_2","unstructured":"Ducoffe M Precioso F. Adversarial active learning for deep networks: a margin based approach. arXiv. 2018. https:\/\/doi.org\/10.48550\/arXiv.1802.09841"},{"key":"e_1_3_2_31_2","unstructured":"Zhu J-J Bento J. Generative adversarial active learning. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1702.07956"},{"key":"e_1_3_2_32_2","unstructured":"Goodfellow I. Generative adversarial nets. Paper presented at: Advances in neural information processing systems; 2014."},{"key":"e_1_3_2_33_2","unstructured":"Tran T Do T-T Reid I Carneiro G. Paper presented at: International Conference on Machine Learning (PMLR 2019) pp. 6295\u20136304."},{"key":"e_1_3_2_34_2","unstructured":"Hacohen G Dekel A Weinshall D. Active learning on a budget: Opposite strategies suit high and low budgets. arXiv. 2022. https:\/\/doi.org\/10.48550\/arXiv.2202.02794"},{"key":"e_1_3_2_35_2","unstructured":"Chen L. Medical Imaging with Deep Learning. 2023."},{"key":"e_1_3_2_36_2","unstructured":"Sener O Savarese S. Active learning for convolutional neural networks: A core-set approach. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1708.00489"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Agarwal S Arora H Anand S Arora C. Computer Vision\u2013ECCV 2020: 16th European Conference Glasgow UK August 23\u201328 2020 Proceedings Part XVI 16 (Springer 2020) pp. 137\u2013153.","DOI":"10.1007\/978-3-030-58517-4_9"},{"issue":"2","key":"e_1_3_2_38_2","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/JSTARS.2016.2598859","article-title":"Active deep learning for classification of hyperspectral images","volume":"10","author":"Liu P","year":"2016","unstructured":"Liu P, Zhang H, Eom KB. Active deep learning for classification of hyperspectral images. IEEE J Sel Topics Appl Earth Observ Remote Sens. 2016;10(2):712.","journal-title":"IEEE J Sel Topics Appl Earth Observ Remote Sens"},{"key":"e_1_3_2_39_2","unstructured":"Geifman Y El-Yaniv R. Deep active learning over the long tail. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1711.00941"},{"key":"e_1_3_2_40_2","unstructured":"Gissin D Shalev-Shwartz S. Discriminative active learning. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1907.06347"},{"key":"e_1_3_2_41_2","unstructured":"Sinha S Ebrahimi S Darrell T. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019;5972\u20135981."},{"key":"e_1_3_2_42_2","unstructured":"Kingma DP Welling M Auto-encoding variational bayes. arXiv. 2013. https:\/\/doi.org\/10.48550\/arXiv.1312.6114"},{"key":"e_1_3_2_43_2","unstructured":"Shui C Zhou F Gagn\u00e9 C Wang B. International Conference on Artificial Intelligence and Statistics (PMLR 2020) pp. 1308\u20131318."},{"key":"e_1_3_2_44_2","unstructured":"Zhdanov F. Diverse mini-batch active learning. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1901.05954"},{"key":"e_1_3_2_45_2","first-page":"11933","article-title":"Batch active learning at scale","volume":"34","author":"Citovsky G","year":"2021","unstructured":"Citovsky G et al. Batch active learning at scale. Adv Neural Inf Proces Syst. 2021;34:11933.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_2_46_2","unstructured":"Wu J Chen J Huang D. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022;9397\u20139406."},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Yin C. Paper presented at: IEEE International Conference on Data Mining (ICDM) (IEEE 2017) pp. 575\u2013584; 2017.","DOI":"10.1109\/ICDM.2017.67"},{"key":"e_1_3_2_48_2","unstructured":"Prabhu V Chandrasekaran A Saenko K Hoffman J. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021;8505\u20138514."},{"key":"e_1_3_2_49_2","unstructured":"B\u0131y\u0131k E Wang K Anari N Sadigh D. Batch active learning using determinantal point processes. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1906.07975"},{"key":"e_1_3_2_50_2","unstructured":"Zhan X Li Q Chan AB. Multiple-criteria based active learning with fixed-size determinantal point processes. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2107.01622"},{"key":"e_1_3_2_51_2","unstructured":"Zhang B et\u00a0al. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020;8756\u20138765."},{"key":"e_1_3_2_52_2","unstructured":"Kim K Park D Kim KI Chun SY. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021;8166\u20138175."},{"key":"e_1_3_2_53_2","unstructured":"Gong J Fan Z Ke Q Rahmani H Liu J. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022;11079\u201311089."},{"key":"e_1_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Bateni P. Beyond simple meta-learning: Multi-purpose models for multi-domain active and continual few-shot learning. arXiv. 2022. https:\/\/doi.org\/10.48550\/arXiv.2201.05151","DOI":"10.2139\/ssrn.4331203"},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Wanyan Y Yang X Chen C Xu C. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023;6492\u20136502.","DOI":"10.1109\/CVPR52729.2023.00628"},{"key":"e_1_3_2_56_2","unstructured":"Liu Z Wang J Gong S Lu H Tao D. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019;6122\u20136131."},{"key":"e_1_3_2_57_2","unstructured":"Casanova A Pinheiro PO Rostamzadeh N Pal CJ. Reinforced active learning for image segmentation. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2002.06583"},{"key":"e_1_3_2_58_2","unstructured":"Pang K Dong M Wu Y Hospedales T. Meta-learning transferable active learning policies by deep reinforcement learning. arXiv. 2018. https:\/\/doi.org\/10.48550\/arXiv.1806.04798"},{"key":"e_1_3_2_59_2","unstructured":"Mittal S Tatarchenko M \u00c7i\u00e7ek \u00d6 Brox T. Parting with illusions about deep active learning. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1912.05361"},{"key":"e_1_3_2_60_2","unstructured":"Odena A Olah C Shlens J. International Conference on Machine Learning (PMLR 2017); 2642\u20132651."},{"issue":"2","key":"e_1_3_2_61_2","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.neucom.2019.01.083","article-title":"Active semi-supervised learning based on self-expressive correlation with generative adversarial networks","volume":"345","author":"Zhang X-Y","year":"2019","unstructured":"Zhang X-Y, Shi H, Zhu X, Li P. Active semi-supervised learning based on self-expressive correlation with generative adversarial networks. Neurocomputing. 2019;345(2):103.","journal-title":"Neurocomputing"},{"key":"e_1_3_2_62_2","unstructured":"Mottaghi A Yeung S. Adversarial representation active learning. arXiv 2019. https:\/\/doi.org\/10.48550\/arXiv.1912.09720"},{"key":"e_1_3_2_63_2","first-page":"22919","article-title":"Lada: Look-ahead data acquisition via augmentation for deep active learning","volume":"34","author":"Kim Y-Y","year":"2021","unstructured":"Kim Y-Y, Song K, Jang J, Moon I-C. Lada: Look-ahead data acquisition via augmentation for deep active learning. Adv Neural Inf Proces Syst. 2021;34:22919.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_2_64_2","unstructured":"Chen Y Jamieson K Du S. International Conference on Machine Learning (PMLR 2022); 3271\u20133298."},{"key":"e_1_3_2_65_2","unstructured":"Attenberg J Provost F. Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining (2010) pp. 423\u2013432."},{"key":"e_1_3_2_66_2","first-page":"19523","article-title":"Beyond neural scaling laws: Beating power law scaling via data pruning","volume":"35","author":"Sorscher B","year":"2022","unstructured":"Sorscher B, Geirhos R, Shekhar S, Ganguli S, Morcos A. Beyond neural scaling laws: Beating power law scaling via data pruning. Adv Neural Inf Proces Syst. 2022;35:19523.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_2_67_2","unstructured":"Yehuda O Dekel A Hacohen G WeinshallD. Active learning through a covering lens. arXiv. 2022. https:\/\/doi.org\/10.48550\/arXiv.2205.11320"},{"key":"e_1_3_2_68_2","unstructured":"Mahmood R Fidler S Law MT. Low budget active learning via wasserstein distance: An integer programming approach. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2106.02968"},{"key":"e_1_3_2_69_2","unstructured":"Chitta K Alvarez JM Haussmann E. Farabet C. Training data distribution search with ensemble active learning; 2019."},{"key":"e_1_3_2_70_2","unstructured":"Fu B Cao Z Wang J Long M. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021;7272\u20137281."},{"key":"e_1_3_2_71_2","unstructured":"Xie B Yuan L Li S Liu CH Cheng X. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022;8068\u20138078."},{"key":"e_1_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Yuan J. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023;15599\u201315608.","DOI":"10.1109\/CVPR52729.2023.01497"},{"key":"e_1_3_2_73_2","doi-asserted-by":"crossref","first-page":"2591","DOI":"10.1109\/TCSVT.2016.2589879","article-title":"Cost-effective active learning for deep image classification","volume":"27","author":"Wang K","year":"2016","unstructured":"Wang K, Zhang D, Li Y, Zhang R, Lin L. Cost-effective active learning for deep image classification. IEEE Trans Circuits Syst Video Technol. 2016;27:2591.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"e_1_3_2_74_2","unstructured":"Gorriz M Carlier A Faure E Giro-i Nieto X. Cost-effective active learning for melanoma segmentation. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1711.09168"},{"key":"e_1_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Gao M. Computer Vision\u2013ECCV 2020: 16th European Conference Glasgow UK August 23\u201328 2020 Proceedings Part X 16 (Springer 2020) pp. 510\u2013526.","DOI":"10.1007\/978-3-030-58607-2_30"},{"key":"e_1_3_2_76_2","unstructured":"Zhang W. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022;20666\u201320676."},{"key":"e_1_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Lourentzou I. Paper presented at: The 14th PErvasive Technologies Related to Assistive Environments Conference (2021) pp. 431\u2013438.","DOI":"10.1145\/3453892.3461321"},{"key":"e_1_3_2_78_2","unstructured":"Sim\u00e9oni O Budnik M Avrithis Y Gravier G. Paper presented at: 25th International Conference on Pattern Recognition (ICPR) (IEEE 2021) pp. 1220\u20131227. 2020."},{"key":"e_1_3_2_79_2","unstructured":"Iscen A Tolias G Avrithis Y Chum O. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019;5070\u20135079."},{"key":"e_1_3_2_80_2","unstructured":"Guo J. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021;2896\u20132905."},{"key":"e_1_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Guo J. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining; 2022. p. 2935\u20132945.","DOI":"10.1145\/3534678.3539022"},{"key":"e_1_3_2_82_2","first-page":"7263","article-title":"Proceedings of the AAAI conference on","volume":"36","author":"Kwak B-W","year":"2022","unstructured":"Kwak B-W, Kim Y, Kim YJ, Hwang S-W, Yeo J. Proceedings of the AAAI conference on. Artif Intell. 2022;36:7263\u20137271.","journal-title":"Artif Intell"},{"key":"e_1_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Bengar JZ van de Weijer J Twardowski B Raducanu B. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021;1631\u20131639.","DOI":"10.1109\/ICCVW54120.2021.00188"},{"key":"e_1_3_2_84_2","unstructured":"Pourahmadi K Nooralinejad P Pirsiavash H. A simple baseline for low-budget active learning. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2110.12033"},{"key":"e_1_3_2_85_2","doi-asserted-by":"crossref","unstructured":"Margatina K Barrault L Aletras N. On the importance of effectively adapting pretrained language models for active learning. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2104.08320","DOI":"10.18653\/v1\/2022.acl-short.93"},{"key":"e_1_3_2_86_2","first-page":"28140","article-title":"Active learning helps pretrained models learn the intended task","volume":"35","author":"Tamkin A","year":"2022","unstructured":"Tamkin A, Nguyen D, Deshpande S, Mu J, Goodman N. Active learning helps pretrained models learn the intended task. Adv Neural Inf Proces Syst. 2022;35:28140.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_2_87_2","doi-asserted-by":"crossref","unstructured":"Xie Y. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023;23715\u201323724.","DOI":"10.1109\/CVPR52729.2023.02271"},{"key":"e_1_3_2_88_2","doi-asserted-by":"crossref","unstructured":"Zhang Y Feng S Tan C. Active example selection for in-context learning. arXiv. 2022. https:\/\/doi.org\/10.48550\/arXiv.2211.04486","DOI":"10.18653\/v1\/2022.emnlp-main.622"},{"key":"e_1_3_2_89_2","doi-asserted-by":"crossref","unstructured":"Liu J. What makes good in-context examples for gpt-3? arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2101.06804","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"e_1_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Margatina K Schick T Aletras N Dwivedi-Yu J. Active learning principles for in-context learning with large language models. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.14264","DOI":"10.18653\/v1\/2023.findings-emnlp.334"},{"key":"e_1_3_2_91_2","unstructured":"Wu Z Wang Y Ye J Kong L. Self-adaptive in-context learning: An information compression perspective for in-context example selection and ordering."},{"key":"e_1_3_2_92_2","unstructured":"Cao Y Kang Y Wang C Sun L. Instruction mining: When data mining meets large language model finetuning. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2307.06290"},{"key":"e_1_3_2_93_2","unstructured":"Chen L. Alpagasus: Training a better alpaca with fewer data. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2307.08701"},{"key":"e_1_3_2_94_2","unstructured":"Hoang TN Hong S Xiao C Low B Sun J. Proceedings of the Web Conference. 2021;2021:3569\u20133581."},{"key":"e_1_3_2_95_2","doi-asserted-by":"crossref","unstructured":"Yi JSK Seo M Park J Choi D-G. Computer Vision\u2013ECCV 2022: 17th European Conference Tel Aviv Israel October 23\u201327 2022 Part XXVI (Springer: Proceedings; 2022. p. 596\u2013612.","DOI":"10.1007\/978-3-031-19809-0_34"},{"key":"e_1_3_2_96_2","unstructured":"Gidaris S Singh P Komodakis N. Unsupervised representation learning by predicting image rotations. arXiv. 2018. https:\/\/doi.org\/10.48550\/arXiv.1803.07728"},{"key":"e_1_3_2_97_2","unstructured":"Wen Z Pizarro O Williams S. NTKCPL: Active learning on top of self-supervised model by estimating true coverage. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2306.04099"},{"key":"e_1_3_2_98_2","doi-asserted-by":"crossref","unstructured":"Yuan M Lin H-T Boyd-Graber J. Cold-start active learning through self-supervised language modeling. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.09535","DOI":"10.18653\/v1\/2020.emnlp-main.637"},{"key":"e_1_3_2_99_2","doi-asserted-by":"crossref","unstructured":"Wang X Lian L Yu SX. Computer Vision\u2013ECCV 2022: 17th European Conference Tel Aviv Israel October 23\u201327 2022 Part XXX (Springer: Proceedings; 2022. p. 427\u2013445.","DOI":"10.1007\/978-3-031-20056-4_25"},{"key":"e_1_3_2_100_2","unstructured":"Chen X Fan H Girshick R He K. Improved baselines with momentum contrastive learning. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2003.0429"},{"key":"e_1_3_2_101_2","unstructured":"Bhatnagar S Goyal S Tank D Sethi A. PAL: pretext-based active learning. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.15947"},{"key":"e_1_3_2_102_2","unstructured":"Du P. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021;8927\u20138936."},{"key":"e_1_3_2_103_2","unstructured":"Caramalau R Bhattarai B Stoyanov D Kim T-K. MoBYv2AL: Self-supervised active learning for image classification. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2301.01531"},{"key":"e_1_3_2_104_2","unstructured":"Cabannes V Bottou L Lecun Y Balestriero R. Active self-supervised learning: A few low-cost relationships are all you need. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2303.15256"},{"issue":"11","key":"e_1_3_2_105_2","doi-asserted-by":"crossref","first-page":"4048","DOI":"10.1109\/JSTARS.2018.2874225","article-title":"Active-learning-incorporated deep transfer learning for hyperspectral image classification","volume":"11","author":"Lin J","year":"2018","unstructured":"Lin J, Zhao L, Li S, Ward R, Wang ZJ. Active-learning-incorporated deep transfer learning for hyperspectral image classification. IEEE J Select Top Appli Earth Observ Remote Sens. 2018;11(11):4048.","journal-title":"IEEE J Select Top Appli Earth Observ Remote Sens"},{"key":"e_1_3_2_106_2","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1007\/s11517-018-1815-2","article-title":"Classification of ecg beats using deep belief network and active learning","volume":"56","author":"Sayantan G","year":"2018","unstructured":"Sayantan G, Kien P, Kadambari K. Classification of ecg beats using deep belief network and active learning. Med Biol Eng Comput. 2018;56:1887.","journal-title":"Med Biol Eng Comput"},{"key":"e_1_3_2_107_2","doi-asserted-by":"crossref","unstructured":"Sadafi A. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference Shenzhen China October 13\u201317 2019 Proceedings Part I 22 (Springer 2019) pp. 685\u2013693.","DOI":"10.1007\/978-3-030-32239-7_76"},{"key":"e_1_3_2_108_2","unstructured":"Choi J Elezi I Lee H-J Farabet C Alvarez JM. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021;10264\u201310273."},{"key":"e_1_3_2_109_2","doi-asserted-by":"crossref","unstructured":"Yang L Zhang Y Chen J Zhang S Chen DZ. Medical Image Computing and Computer Assisted Intervention- MICCAI 2017: 20th International Conference Quebec City QC Canada September 11-13 2017 Proceedings Part III 20 (Springer 2017) pp. 399\u2013407.","DOI":"10.1007\/978-3-319-66179-7_46"},{"issue":"1","key":"e_1_3_2_110_2","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1109\/TITS.2022.3218403","article-title":"An active and contrastive learning framework for fine-grained off-road semantic segmentation","volume":"24","author":"Gao B","year":"2022","unstructured":"Gao B, Zhao X, Zhao H. An active and contrastive learning framework for fine-grained off-road semantic segmentation. IEEE Trans Intell Transp Syst. 2022;24(1):564\u2013579.","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"e_1_3_2_111_2","unstructured":"Cai L Xu X Liew JH Foo CS. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021;10988\u201310997."},{"key":"e_1_3_2_112_2","unstructured":"Kirillov A. Segment anything. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2304.02643"},{"key":"e_1_3_2_113_2","unstructured":"Zhang P Xu X Xiong D. Paper presented at: International Conference on Asian Language Processing (IALP) (IEEE 2018); 2018."},{"key":"e_1_3_2_114_2","doi-asserted-by":"crossref","unstructured":"Zhao Y Zhang H Zhou S Zhang Z. Findings of the Association for Computational Linguistics: EMNLP. 2020;2020:1796\u20131806.","DOI":"10.18653\/v1\/2020.findings-emnlp.162"},{"key":"e_1_3_2_115_2","doi-asserted-by":"crossref","unstructured":"Prabhu A Dognin C Singh M. Sampling bias in deep active classification: An empirical study. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1909.09389","DOI":"10.18653\/v1\/D19-1417"},{"key":"e_1_3_2_116_2","unstructured":"Radmard P Fathullah Y Lipani A. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2021) pp. 4310\u20134321."},{"key":"e_1_3_2_117_2","doi-asserted-by":"crossref","unstructured":"Li Z Qu L Cohen PR Tumuluri RV Haffari G. The best of both worlds: Combining human and machine translations for multilingual semantic parsing with active learning. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.12737","DOI":"10.18653\/v1\/2023.acl-long.529"},{"issue":"4","key":"e_1_3_2_118_2","doi-asserted-by":"crossref","first-page":"1796","DOI":"10.1121\/1.5004570","article-title":"Active learning for bird sound classification via a kernel-based extreme learning machine","volume":"142","author":"Qian K","year":"2017","unstructured":"Qian K, Zhang Z, Baird A, Schuller B. Active learning for bird sound classification via a kernel-based extreme learning machine. J Acoust Soc Am. 2017;142(4):1796.","journal-title":"J Acoust Soc Am"},{"key":"e_1_3_2_119_2","unstructured":"Abdelwahab M Busso C. Paper presented at: 8th International Conference on Affective Computing and Intelligent Interaction (ACII) (IEEE 2019); 2019."},{"key":"e_1_3_2_120_2","unstructured":"Ma S Zeng Z McDuff D Song Y. Active contrastive learning of audio-visual video representations. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2009.09805"},{"key":"e_1_3_2_121_2","unstructured":"Farquhar S Gal Y Rainforth T. On statistical bias in active learning: How and when to fix it. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2101.11665"}],"container-title":["Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/icomputing.0058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T09:12:42Z","timestamp":1730452362000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/icomputing.0058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":120,"alternative-id":["10.34133\/icomputing.0058"],"URL":"https:\/\/doi.org\/10.34133\/icomputing.0058","relation":{},"ISSN":["2771-5892"],"issn-type":[{"value":"2771-5892","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2023-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0058"}}