{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:21:43Z","timestamp":1743114103842,"version":"3.40.3"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585730"},{"type":"electronic","value":"9783030585747"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58574-7_26","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T16:19:07Z","timestamp":1605197947000},"page":"431-447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Weight Decay Scheduling and Knowledge Distillation for Active Learning"],"prefix":"10.1007","author":[{"given":"Juseung","family":"Yun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byungjoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junmo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"26_CR1","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Advances in Neural Information Processing Systems, pp. 2654\u20132662 (2014)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Beluch, W.H., Genewein, T., N\u00fcrnberger, A., K\u00f6hler, J.M.: The power of ensembles for active learning in image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9368\u20139377 (2018)","DOI":"10.1109\/CVPR.2018.00976"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. arXiv preprint arXiv:1909.13719 (2019)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Elhamifar, E., Sapiro, G., Yang, A., Shankar Sasrty, S.: A convex optimization framework for active learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 209\u2013216 (2013)","DOI":"10.1109\/ICCV.2013.33"},{"key":"26_CR5","doi-asserted-by":"publisher","unstructured":"Freytag, A., Rodner, E., Denzler, J.: Selecting influential examples: active learning with expected model output changes. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 562\u2013577. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_37","DOI":"10.1007\/978-3-319-10593-2_37"},{"key":"26_CR6","unstructured":"Gal, Y., Islam, R., Ghahramani, Z.: Deep Bayesian active learning with image data. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1183\u20131192. JMLR.org (2017)"},{"key":"26_CR7","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315\u2013323 (2011)"},{"key":"26_CR8","unstructured":"Guo, Y.: Active instance sampling via matrix partition. In: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2010)"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1921\u20131930 (2019)","DOI":"10.1109\/ICCV.2019.00201"},{"key":"26_CR11","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"26_CR12","unstructured":"Hoffer, E., Banner, R., Golan, I., Soudry, D.: Norm matters: efficient and accurate normalization schemes in deep networks. In: Advances in Neural Information Processing Systems, pp. 2160\u20132170 (2018)"},{"key":"26_CR13","unstructured":"Hu, P., Lipton, Z.C., Anandkumar, A., Ramanan, D.: Active learning with partial feedback. arXiv preprint arXiv:1802.07427 (2018)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"26_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"26_CR16","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"26_CR17","unstructured":"Jastrz\u0119bski, S., et al.: Three factors influencing minima in SGD. arXiv preprint arXiv:1711.04623 (2017)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2372\u20132379. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206627"},{"key":"26_CR19","unstructured":"K\u00e4ding, C., Rodner, E., Freytag, A., Denzler, J.: Active and continuous exploration with deep neural networks and expected model output changes. arXiv preprint arXiv:1612.06129 (2016)"},{"key":"26_CR20","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. arXiv preprint arXiv:1609.04836 (2016)"},{"key":"26_CR21","unstructured":"Khodabandeh, M., Deng, Z., Ibrahim, M.S., Satoh, S., Mori, G.: Active learning for structured prediction from partially labeled data. arXiv preprint arXiv:1706.02342 (2017)"},{"key":"26_CR22","unstructured":"Kim, J., Park, S., Kwak, N.: Paraphrasing complex network: network compression via factor transfer. In: Advances in Neural Information Processing Systems, pp. 2760\u20132769 (2018)"},{"key":"26_CR23","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"26_CR24","unstructured":"Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: Advances in Neural Information Processing Systems, pp. 950\u2013957 (1992)"},{"issue":"11","key":"26_CR25","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: Machine Learning Proceedings 1994, pp. 148\u2013156. Elsevier (1994)","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"key":"26_CR27","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-1-4471-2099-5_1","volume-title":"SIGIR 1994","author":"DD Lewis","year":"1994","unstructured":"Lewis, D.D., Gale, W.A.: A sequential algorithm for training text classifiers. In: Croft, B.W., van Rijsbergen, C.J. (eds.) SIGIR 1994, pp. 3\u201312. Springer, London (1994). https:\/\/doi.org\/10.1007\/978-1-4471-2099-5_1"},{"key":"26_CR28","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. In: Advances in Neural Information Processing Systems, pp. 6389\u20136399 (2018)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"26_CR30","unstructured":"Luo, W., Schwing, A., Urtasun, R.: Latent structured active learning. In: Advances in Neural Information Processing Systems, pp. 728\u2013736 (2013)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Meyer, B.J., Drummond, T.: The importance of metric learning for robotic vision: open set recognition and active learning. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 2924\u20132931. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794188"},{"key":"26_CR32","unstructured":"Neelakantan, A., et al.: Adding gradient noise improves learning for very deep networks. arXiv preprint arXiv:1511.06807 (2015)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Nguyen, H.T., Smeulders, A.: Active learning using pre-clustering. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 79 (2004)","DOI":"10.1145\/1015330.1015349"},{"key":"26_CR34","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"26_CR35","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"26_CR36","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/11871842_40","volume-title":"Machine Learning: ECML 2006","author":"D Roth","year":"2006","unstructured":"Roth, D., Small, K.: Margin-based active learning for structured output spaces. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 413\u2013424. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_40"},{"key":"26_CR37","unstructured":"Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. arXiv preprint arXiv:1708.00489 (2017)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Settles, B., Craven, M.: An analysis of active learning strategies for sequence labeling tasks. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 1070\u20131079 (2008)","DOI":"10.3115\/1613715.1613855"},{"key":"26_CR39","unstructured":"Settles, B., Craven, M., Ray, S.: Multiple-instance active learning. In: Advances in Neural Information Processing Systems, pp. 1289\u20131296 (2008)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Shen, Y., Yun, H., Lipton, Z.C., Kronrod, Y., Anandkumar, A.: Deep active learning for named entity recognition. arXiv preprint arXiv:1707.05928 (2017)","DOI":"10.18653\/v1\/W17-2630"},{"key":"26_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"1","key":"26_CR42","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"26_CR43","unstructured":"Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 2(Nov), 45\u201366 (2001)"},{"key":"26_CR44","unstructured":"Van Laarhoven, T.: L2 regularization versus batch and weight normalization. arXiv preprint arXiv:1706.05350 (2017)"},{"issue":"1\u20132","key":"26_CR45","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s11263-014-0721-9","volume":"108","author":"S Vijayanarasimhan","year":"2014","unstructured":"Vijayanarasimhan, S., Grauman, K.: Large-scale live active learning: Training object detectors with crawled data and crowds. Int. J. Comput. Vision 108(1\u20132), 97\u2013114 (2014)","journal-title":"Int. J. Comput. Vision"},{"issue":"12","key":"26_CR46","doi-asserted-by":"publisher","first-page":"2591","DOI":"10.1109\/TCSVT.2016.2589879","volume":"27","author":"K Wang","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. 27(12), 2591\u20132600 (2016)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Xie, Q., Hovy, E., Luong, M.T., Le, Q.V.: Self-training with noisy student improves imagenet classification. arXiv preprint arXiv:1911.04252 (2019)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4133\u20134141 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Yoo, D., Kweon, I.S.: Learning loss for active learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 93\u2013102 (2019)","DOI":"10.1109\/CVPR.2019.00018"},{"key":"26_CR50","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)"},{"key":"26_CR51","unstructured":"Zhang, G., Wang, C., Xu, B., Grosse, R.: Three mechanisms of weight decay regularization. arXiv preprint arXiv:1810.12281 (2018)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58574-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:09:57Z","timestamp":1731370197000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58574-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585730","9783030585747"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58574-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}