{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:12:59Z","timestamp":1783437179070,"version":"3.54.6"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439957","type":"print"},{"value":"9783031439964","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43996-4_7","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"68-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery"],"prefix":"10.1007","author":[{"given":"Long","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mobarakol","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"7_CR1","unstructured":"Allan, M., et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"7_CR2","unstructured":"Allan, M., et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Seenivasan, L., Ren, H.: Surgical-VQLA: transformer with gated vision-language embedding for visual question localized-answering in robotic surgery. arXiv preprint arXiv:2305.11692 (2023)","DOI":"10.1109\/ICRA48891.2023.10160403"},{"issue":"7","key":"7_CR4","first-page":"3366","volume":"44","author":"M De Lange","year":"2021","unstructured":"De Lange, M., et al.: A continual learning survey: defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell. 44(7), 3366\u20133385 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR5","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR6","doi-asserted-by":"publisher","unstructured":"Derakhshani, M.M., et al.: Lifelonger: a benchmark for continual disease classification. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. MICCAI 2022. LNCS, vol. 13432, pp. 314\u2013324. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16434-7_31","DOI":"10.1007\/978-3-031-16434-7_31"},{"key":"7_CR7","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":"7_CR8","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":"7_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"7_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-030-59716-0_60","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"M Islam","year":"2020","unstructured":"Islam, M., Seenivasan, L., Ming, L.C., Ren, H.: Learning and reasoning with the graph structure representation in robotic surgery. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 627\u2013636. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_60"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Jin, A., et al.: Tool detection and operative skill assessment in surgical videos using region-based convolutional neural networks. In: IEEE Winter Conference on Applications of Computer Vision (2018)","DOI":"10.1109\/WACV.2018.00081"},{"key":"7_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"6","key":"7_CR13","doi-asserted-by":"publisher","first-page":"e279","DOI":"10.1016\/S2589-7500(20)30102-3","volume":"2","author":"CS Lee","year":"2020","unstructured":"Lee, C.S., Lee, A.Y.: Clinical applications of continual learning machine learning. Lancet Digit. Health 2(6), e279\u2013e281 (2020)","journal-title":"Lancet Digit. Health"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Lei, S.W., et al.: Symbolic replay: scene graph as prompt for continual learning on VQA task. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 1250\u20131259 (2023)","DOI":"10.1609\/aaai.v37i1.25208"},{"key":"7_CR15","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"issue":"12","key":"7_CR16","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935\u20132947 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR17","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. arXiv preprint arXiv:2111.10056 (2021)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Liu, J.J., Hou, Q., Cheng, M.M., Wang, C., Feng, J.: Improving convolutional networks with self-calibrated convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10096\u201310105 (2020)","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Michieli, U., Zanuttigh, P.: Incremental learning techniques for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00400"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001\u20132010 (2017)","DOI":"10.1109\/CVPR.2017.587"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"7_CR22","doi-asserted-by":"publisher","unstructured":"Seenivasan, L., Islam, M., Krishna, A., Ren, H.: Surgical-VQA: visual question answering in surgical scenes using transformer. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. MICCAI 2022. LNCS, vol. 13437, pp. 33\u201343. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_4","DOI":"10.1007\/978-3-031-16449-1_4"},{"key":"7_CR23","first-page":"29440","volume":"35","author":"T Srinivasan","year":"2022","unstructured":"Srinivasan, T., Chang, T.Y., Pinto Alva, L., Chochlakis, G., Rostami, M., Thomason, J.: Climb: a continual learning benchmark for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 35, 29440\u201329453 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Stauder, R., Ostler, D., Kranzfelder, M., Koller, S., Feu\u00dfner, H., Navab, N.: The tum lapchole dataset for the m2cai 2016 workflow challenge. arXiv preprint arXiv:1610.09278 (2016)","DOI":"10.1515\/iss-2017-0035"},{"issue":"1","key":"7_CR25","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F.E., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3903\u20133911 (2020)","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.T.: Maintaining discrimination and fairness in class incremental learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13208\u201313217 (2020)","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, D.W., Wang, F.Y., Ye, H.J., Zhan, D.C.: PyCIL: a python toolbox for class-incremental learning (2021)","DOI":"10.1145\/3474085.3475306"},{"key":"7_CR29","unstructured":"Zhu, F., Cheng, Z., Zhang, X.Y., Liu, C.L.: Class-incremental learning via dual augmentation. Adv. Neural Inf. Process. Syst. 34, 14306\u201314318 (2021)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhang, X.Y., Wang, C., Yin, F., Liu, C.L.: Prototype augmentation and self-supervision for incremental learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5871\u20135880 (2021)","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, K., Zhai, W., Cao, Y., Luo, J., Zha, Z.J.: Self-sustaining representation expansion for non-exemplar class-incremental learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9296\u20139305 (2022)","DOI":"10.1109\/CVPR52688.2022.00908"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Zou, W., Ye, T., Zheng, W., Zhang, Y., Chen, L., Wu, Y.: Self-calibrated efficient transformer for lightweight super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 930\u2013939 (2022)","DOI":"10.1109\/CVPRW56347.2022.00107"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43996-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T16:03:39Z","timestamp":1720109019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43996-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439957","9783031439964"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43996-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","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":"2250","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":"730","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":"32% - 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":"5","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)"}}]}}