{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:03:10Z","timestamp":1761897790853,"version":"3.40.3"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198298"},{"type":"electronic","value":"9783031198304"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19830-4_13","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"218-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DistPro: Searching a\u00a0Fast Knowledge Distillation Process via\u00a0Meta Optimization"],"prefix":"10.1007","author":[{"given":"Xueqing","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shawn","family":"Newsam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"unstructured":"Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981\u20133989 (2016)","key":"13_CR1"},{"doi-asserted-by":"crossref","unstructured":"Bucilu\u0103, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535\u2013541 (2006)","key":"13_CR2","DOI":"10.1145\/1150402.1150464"},{"unstructured":"Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"13_CR3"},{"doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Zhao, H., Jia, J.: Distilling knowledge via knowledge review. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5008\u20135017 (2021)","key":"13_CR4","DOI":"10.1109\/CVPR46437.2021.00497"},{"issue":"3","key":"13_CR5","first-page":"1","volume":"12","author":"Z Chen","year":"2018","unstructured":"Chen, Z., Liu, B.: Lifelong machine learning. Synth. Lect. Artif. Intell. Mach. Learn. 12(3), 1\u2013207 (2018)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","key":"13_CR6","DOI":"10.1109\/CVPR.2016.350"},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale Hierarchical Image Database. In: CVPR09 (2009)","key":"13_CR7","DOI":"10.1109\/CVPR.2009.5206848"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)","key":"13_CR8"},{"unstructured":"Dosovitskiy, A., et al.: An image is worth 16 x 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)","key":"13_CR9"},{"unstructured":"Franceschi, L., Frasconi, P., Salzo, S., Grazzi, R., Pontil, M.: Bilevel programming for hyperparameter optimization and meta-learning. In: International Conference on Machine Learning, pp. 1568\u20131577. PMLR (2018)","key":"13_CR10"},{"issue":"6","key":"13_CR11","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129(6), 1789\u20131819 (2021)","journal-title":"Int. J. Comput. Vision"},{"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)","key":"13_CR12","DOI":"10.1109\/CVPR.2016.90"},{"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\/CVF International Conference on Computer Vision, pp. 1921\u20131930 (2019)","key":"13_CR13","DOI":"10.1109\/ICCV.2019.00201"},{"unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)","key":"13_CR14"},{"unstructured":"Hoffer, E., Hubara, I., Soudry, D.: Train longer, generalize better: closing the generalization gap in large batch training of neural networks. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"13_CR15"},{"unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)","key":"13_CR16"},{"unstructured":"Huang, Z., Wang, N.: Like what you like: knowledge distill via neuron selectivity transfer. arXiv preprint arXiv:1707.01219 (2017)","key":"13_CR17"},{"unstructured":"Jang, Y., Lee, H., Hwang, S.J., Shin, J.: Learning what and where to transfer. In: International Conference on Machine Learning, pp. 3030\u20133039. PMLR (2019)","key":"13_CR18"},{"doi-asserted-by":"crossref","unstructured":"Ji, M., Heo, B., Park, S.: Show, attend and distill: Knowledge distillation via attention-based feature matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 7945\u20137952 (2021)","key":"13_CR19","DOI":"10.1609\/aaai.v35i9.16969"},{"unstructured":"Kimura, A., Ghahramani, Z., Takeuchi, K., Iwata, T., Ueda, N.: Few-shot learning of neural networks from scratch by pseudo example optimization. arXiv preprint arXiv:1802.03039 (2018)","key":"13_CR20"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"13_CR21"},{"unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)","key":"13_CR22"},{"unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)","key":"13_CR23"},{"unstructured":"Lee, S., Song, B.C.: Graph-based knowledge distillation by multi-head attention network. arXiv preprint arXiv:1907.02226 (2019)","key":"13_CR24"},{"unstructured":"Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. In: International Conference on Learning Representations (2019)","key":"13_CR25"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2604\u20132613 (2019)","key":"13_CR26","DOI":"10.1109\/CVPR.2019.00271"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Search to distill: Pearls are everywhere but not the eyes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7539\u20137548 (2020)","key":"13_CR27","DOI":"10.1109\/CVPR42600.2020.00756"},{"doi-asserted-by":"crossref","unstructured":"Lyu, L., Chen, C.H.: Differentially private knowledge distillation for mobile analytics. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1809\u20131812 (2020)","key":"13_CR28","DOI":"10.1145\/3397271.3401259"},{"doi-asserted-by":"crossref","unstructured":"Ma, F., Karaman, S.: Sparse-to-dense: depth prediction from sparse depth samples and a single image. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 4796\u20134803. IEEE (2018)","key":"13_CR29","DOI":"10.1109\/ICRA.2018.8460184"},{"doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","key":"13_CR30","DOI":"10.1007\/978-3-030-01264-9_8"},{"unstructured":"M\u00fcller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? Adv. Neural Inf. Process. Syst. 32 (2019)","key":"13_CR31"},{"key":"13_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"unstructured":"Oord, A., et al.: Parallel wavenet: fast high-fidelity speech synthesis. In: International Conference on Machine Learning, pp. 3918\u20133926. PMLR (2018)","key":"13_CR33"},{"unstructured":"Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. In: International Conference on Machine Learning, pp. 4334\u20134343. PMLR (2018)","key":"13_CR34"},{"unstructured":"Romero, A., Ballas, N., Kahou, S., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. CoRR abs\/1412.6550 (2015)","key":"13_CR35"},{"doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","key":"13_CR36","DOI":"10.1109\/CVPR.2018.00474"},{"doi-asserted-by":"crossref","unstructured":"Shang, Y., Duan, B., Zong, Z., Nie, L., Yan, Y.: Lipschitz continuity guided knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10675\u201310684 (2021)","key":"13_CR37","DOI":"10.1109\/ICCV48922.2021.01050"},{"unstructured":"Shen, Z., Xing, E.: A fast knowledge distillation framework for visual recognition. arXiv preprint arXiv:2112.01528 (2021)","key":"13_CR38"},{"unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: International Conference on Learning Representations (2020)","key":"13_CR39"},{"unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)","key":"13_CR40"},{"doi-asserted-by":"crossref","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1365\u20131374 (2019)","key":"13_CR41","DOI":"10.1109\/ICCV.2019.00145"},{"unstructured":"Urner, R., Shalev-Shwartz, S., Ben-David, S.: Access to unlabeled data can speed up prediction time. In: ICML (2011)","key":"13_CR42"},{"unstructured":"Wang, X., Zhang, R., Sun, Y., Qi, J.: Kdgan: knowledge distillation with generative adversarial networks. In: NeurIPS, pp. 783\u2013794 (2018)","key":"13_CR43"},{"key":"13_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58571-6_21","volume-title":"Computer Vision","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Zhou, W., Jiang, T., Bai, X., Xu, Y.: Intra-class feature variation distillation for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 346\u2013362. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_21"},{"key":"13_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-58558-7_15","volume-title":"Computer Vision","author":"L Xiang","year":"2020","unstructured":"Xiang, L., Ding, G., Han, J.: Learning from multiple experts: self-paced knowledge distillation for long-tailed classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 247\u2013263. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_15"},{"unstructured":"Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=rylqooRqK7","key":"13_CR46"},{"doi-asserted-by":"crossref","unstructured":"Xu, G., Liu, Z., Li, X., Loy, C.C.: Knowledge distillation meets self-supervision. In: European Conference on Computer Vision (ECCV) (2020)","key":"13_CR47","DOI":"10.1007\/978-3-030-58545-7_34"},{"doi-asserted-by":"crossref","unstructured":"Yao, L., Pi, R., Xu, H., Zhang, W., Li, Z., Zhang, T.: Joint-detnas: upgrade your detector with NAS, pruning and dynamic distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10175\u201310184 (2021)","key":"13_CR48","DOI":"10.1109\/CVPR46437.2021.01004"},{"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)","key":"13_CR49","DOI":"10.1109\/CVPR.2017.754"},{"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":"13_CR50"},{"doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","key":"13_CR51","DOI":"10.5244\/C.30.87"},{"doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","key":"13_CR52","DOI":"10.1109\/CVPR.2018.00716"},{"doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, Y.: Student customized knowledge distillation: bridging the gap between student and teacher. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5057\u20135066 (2021)","key":"13_CR53","DOI":"10.1109\/ICCV48922.2021.00501"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19830-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:54:33Z","timestamp":1666396473000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19830-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198298","9783031198304"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19830-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}