{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:52:12Z","timestamp":1781218332438,"version":"3.54.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695378","type":"print"},{"value":"9783030695385","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69538-5_3","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T21:16:40Z","timestamp":1614201400000},"page":"36-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Introspective Learning by Distilling Knowledge from Online Self-explanation"],"prefix":"10.1007","author":[{"given":"Jindong","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiliang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1016\/S0896-6273(00)80734-5","volume":"22","author":"S Kastner","year":"1999","unstructured":"Kastner, S., Pinsk, M.A., Weerd, P.D., Desimone, R., Ungerleider, L.G.: Increased activity in human visual cortex during directed attention in the absence of visual stimulation. Neuron 22, 751\u2013761 (1999)","journal-title":"Neuron"},{"key":"3_CR2","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: ICLR (2013)"},{"key":"3_CR3","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.A.: Striving for simplicity: the all convolutional net. In: ICLR (2014)"},{"key":"3_CR4","unstructured":"Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: ICML (2017)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D., et al.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3_CR6","unstructured":"Gu, J., Tresp, V.: Contextual prediction difference analysis for explaining individual image classifications. arXiv preprint arXiv:1910.09086 (2019)"},{"issue":"2","key":"3_CR7","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1037\/0022-3514.60.2.181","volume":"60","author":"TD Wilson","year":"1991","unstructured":"Wilson, T.D., Schooler, J.W.: Thinking too much: introspection can reduce the quality of preferences and decisions. J. Pers. Soc. Psychol. 60(2), 181\u2013192 (1991)","journal-title":"J. Pers. Soc. Psychol."},{"key":"3_CR8","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.concog.2016.04.008","volume":"42","author":"T Leisti","year":"2016","unstructured":"Leisti, T., H\u00e4kkinen, J.: The effect of introspection on judgment and decision making is dependent on the quality of conscious thinking. Conscious. Cogn. 42, 340\u2013351 (2016)","journal-title":"Conscious. Cogn."},{"issue":"5\u20136","key":"3_CR9","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., Vashist, A.: A new learning paradigm: learning using privileged information. Neural Netw. Off. J. Int. Neural Netw. Soc. 22(5\u20136), 544\u2013557 (2009)","journal-title":"Neural Netw. Off. J. Int. Neural Netw. Soc."},{"key":"3_CR10","first-page":"2023","volume":"16","author":"V Vapnik","year":"2015","unstructured":"Vapnik, V., Izmailov, R.: Learning using privileged information: similarity control and knowledge transfer. J. Mach. Learn. Res. 16, 2023\u20132049 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR11","unstructured":"Lopez-Paz, D., Bottou, L., Sch\u00f6lkopf, B., Vapnik, V.: Unifying distillation and privileged information. In: ICLR (2015)"},{"key":"3_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. stat 1050, 9 2015"},{"key":"3_CR13","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep? In: NeurIPS (2013)"},{"key":"3_CR14","unstructured":"Ancona, M.B., Ceolini, E., \u00d6ztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks. In: ICLR (2017)"},{"key":"3_CR15","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One 10, e0130140 (2015)","journal-title":"PLoS One"},{"key":"3_CR16","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., Wattenberg, M.: SmoothGrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)"},{"key":"3_CR17","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML (2017)"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/978-3-030-20893-6_8","volume-title":"Computer Vision \u2013 ACCV 2018","author":"J Gu","year":"2019","unstructured":"Gu, J., Yang, Y., Tresp, V.: Understanding individual decisions of CNNs via contrastive backpropagation. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 119\u2013134. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_8"},{"key":"3_CR19","unstructured":"Gu, J., Tresp, V.: Saliency methods for explaining adversarial attacks. arXiv preprint arXiv:1908.08413 (2019)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3_CR21","unstructured":"Pereyra, G., Tucker, G., Chorowski, J., Kaiser, \u0141., Hinton, G.: Regularizing neural networks by penalizing confident output distributions. In: ICLR Workshop (2017)"},{"key":"3_CR22","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, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce, 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)","DOI":"10.1145\/1150402.1150464"},{"key":"3_CR24","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: ICLR (2014)"},{"key":"3_CR25","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (2016)"},{"key":"3_CR26","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: CVPR, pp. 4133\u20134141 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F.E., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"3_CR28","unstructured":"Furlanello, T., Lipton, Z.C., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks. In: ICML (2018)"},{"key":"3_CR29","unstructured":"Gu, J., Tresp, V.: Search for better students to learn distilled knowledge. arXiv preprint arXiv:2001.11612 (2020)"},{"key":"3_CR30","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: CVPR (2018) 4320\u20134328"},{"key":"3_CR31","unstructured":"Krizhevsky, A., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)"},{"key":"3_CR32","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: 2003 The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers, vol. 2, pp. 1398\u20131402. IEEE (2003)"},{"key":"3_CR33","series-title":"Grundlehren der mathematischen Wissenschaften (A Series of Comprehensive Studies in Mathematics)","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-540-71050-9_6","volume-title":"Optimal Transport","author":"C Villani","year":"2009","unstructured":"Villani, C.: The Wasserstein distances. In: Villani, C. (ed.) Optimal Transport. Grundlehren der mathematischen Wissenschaften (A Series of Comprehensive Studies in Mathematics), vol. 338, pp. 93\u2013111. Springer, Berlin (2009). https:\/\/doi.org\/10.1007\/978-3-540-71050-9_6"},{"key":"3_CR34","unstructured":"Goodfellow, I.: Efficient per-example gradient computations. Technical report, Google Inc., Mountain View, CA, (2015)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S.I., Farajtabar, M., Li, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant: bridging the gap between student and teacher. arXiv preprint arXiv:1902.03393 (2019)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR37","unstructured":"Muller, R.J., Kornblith, S., Hinton, G.E.: When does label smoothing help? ArXiv abs\/1906.02629 (2019)"},{"key":"3_CR38","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. In: ICLR (2017)"},{"key":"3_CR39","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., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"3_CR40","unstructured":"Crowley, E.J., Gray, G., Storkey, A.J.: Moonshine: distilling with cheap convolutions. In: Advances in Neural Information Processing Systems, pp. 2888\u20132898 (2018)"},{"key":"3_CR41","unstructured":"Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: NeurIPS, pp. 9525\u20139536 (2018)"},{"key":"3_CR42","unstructured":"Gu, J., Tresp, V.: Semantics for global and local interpretation of deep neural networks. arXiv preprint arXiv:1910.09085 (2019)"},{"key":"3_CR43","unstructured":"Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning, pp. 2668\u20132677. PMLR (2018)"},{"key":"3_CR44","unstructured":"Gu, J., Tresp, V.: Neural network memorization dissection. arXiv preprint arXiv:1911.09537 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69538-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T21:59:36Z","timestamp":1671400776000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69538-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695378","9783030695385"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69538-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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.","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)"}}]}}