{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:09:28Z","timestamp":1743091768882,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208691"},{"type":"electronic","value":"9783030208707"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20870-7_39","type":"book-chapter","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T16:14:21Z","timestamp":1558714461000},"page":"632-648","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Forget and Diversify: Regularized Refinement for Weakly Supervised Object Detection"],"prefix":"10.1007","author":[{"given":"Jeany","family":"Son","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Solae","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suha","family":"Kwak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohyung","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,25]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Bilen, H., Pedersoli, M., Tuytelaars, T.: Weakly supervised object detection with posterior regularization. In: BMVC (2014)","DOI":"10.5244\/C.28.52"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"39_CR3","unstructured":"Cho, M., Lee, K.M.: Mode-seeking on graphs via random walks. In: CVPR (2012)"},{"key":"39_CR4","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TPAMI.2016.2535231","volume":"39","author":"RG Cinbis","year":"2017","unstructured":"Cinbis, R.G., Verbeek, J., Schmid, C.: Weakly supervised object localization with multi-fold multiple instance learning. TPAMI 39, 189\u2013203 (2017)","journal-title":"TPAMI"},{"key":"39_CR5","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379\u2013387 (2016)"},{"key":"39_CR6","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Pazandeh, A., Pirsiavash, H., Van Gool, L.: Weakly supervised cascaded convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.545"},{"issue":"1","key":"39_CR8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T.G., Lathrop, R.H., Lozano-P\u00e9rez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1), 31\u201371 (1997)","journal-title":"Artif. Intell."},{"key":"39_CR9","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00454-002-2885-2","volume":"28","author":"H Edelsbrunner","year":"2002","unstructured":"Edelsbrunner, H., Letscher, D., Zomorodian, A.: Topological persistence and simplification. Discrete Comput. Geom. 28, 511\u2013533 (2002)","journal-title":"Discrete Comput. Geom."},{"issue":"1","key":"39_CR10","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. IJCV 111(1), 98\u2013136 (2015)","journal-title":"IJCV"},{"issue":"2","key":"39_CR11","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"1","key":"39_CR13","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2016","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. TPAMI 38(1), 142\u2013158 (2016)","journal-title":"TPAMI"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Han, B., Sim, J., Adam, H.: Branchout: regularization for online ensemble tracking with convolutional neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.63"},{"key":"39_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, Y., 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":"39_CR16","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Jie, Z., Wei, Y., Jin, X., Feng, J., Liu, W.: Deep self-taught learning for weakly supervised object localization. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.457"},{"key":"39_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-319-46454-1_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Kantorov","year":"2016","unstructured":"Kantorov, V., Oquab, M., Cho, M., Laptev, I.: ContextLocNet: context-aware deep network models for weakly supervised localization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 350\u2013365. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_22"},{"key":"39_CR19","unstructured":"Kingma, D.P., Salimans, T., Welling, M.: Variational dropout and the local reparameterization trick. In: NIPS (2015)"},{"key":"39_CR20","unstructured":"Krasin, I., et al.: Openimages: A public dataset for large-scale multi-label and multi-class image classification (2017). Dataset available from https:\/\/storage.googleapis.com\/openimages\/web\/index.html"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Lai, B., Gong, X.: Saliency guided end-to-end learning for weakly supervised object detection. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/285"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Li, D., Huang, J., Li, Y., Wang, S., Yang, M.H.: Weakly supervised object localization with progressive domain adaptation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.382"},{"key":"39_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"39_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"39_CR25","unstructured":"Noh, H., You, T., Mun, J., Han, B.: Regularizing deep neural networks by noise: its interpretation and optimization. In: NIPS (2017)"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free? - weakly-supervised learning with convolutional neural networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 6517\u20136525 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"39_CR29","unstructured":"Reed, R., Oh, S., Marks, R.: Regularization using jittered training data. In: IJCNN (1992)"},{"key":"39_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Seo, S., Seo, P.H., Han, B.: Confidence calibration in deep neural networks through stochastic inferences. In: arXiv preprint arXiv:1809.10877 (2018)","DOI":"10.1109\/CVPR.2019.00924"},{"key":"39_CR32","doi-asserted-by":"crossref","unstructured":"Sheikh, Y.A., Khan, E.A., Kanade, T.: Mode-seeking by medoidshifts. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408978"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Shen, Y., Ji, R., Zhang, S., Zuo, W., Wang, Y.: Generative adversarial learning towards fast weakly supervised detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00604"},{"key":"39_CR34","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"39_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-642-33709-3_6","volume-title":"Computer Vision \u2013 ECCV 2012","author":"S Singh","year":"2012","unstructured":"Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, pp. 73\u201386. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33709-3_6"},{"key":"39_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1007\/978-3-642-33712-3_43","volume-title":"Computer Vision \u2013 ECCV 2012","author":"P Siva","year":"2012","unstructured":"Siva, P., Russell, C., Xiang, T.: In defence of negative mining for annotating weakly labelled data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 594\u2013608. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_43"},{"key":"39_CR37","unstructured":"Song, H.O., Lee, Y.J., Jegelka, S., Darrell, T.: Weakly-supervised discovery of visual pattern configurations. In: NIPS (2014)"},{"issue":"1","key":"39_CR38","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":"39_CR39","doi-asserted-by":"crossref","unstructured":"Tang, P., Wang, X., Bai, X., Liu, W.: Multiple instance detection network with online instance classifier refinement. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.326"},{"key":"39_CR40","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. IJCV 104, 154\u2013171 (2013)","journal-title":"IJCV"},{"key":"39_CR41","doi-asserted-by":"crossref","unstructured":"Wan, F., Wei, P., Jiao, J., Han, Z., Ye, Q.: Min-entropy latent model for weakly supervised object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00141"},{"key":"39_CR42","unstructured":"Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: ICML (2013)"},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Xie, L., Wang, J., Wei, Z., Wang, M., Tian, Q.: Disturblabel: regularizing CNN on the loss layer. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.514"},{"key":"39_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, X., Feng, J., Xiong, H., Tian, Q.: Zigzag learning for weakly supervised object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00448"},{"key":"39_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Bai, Y., Ding, M., Li, Y., Ghanem, B.: W2f: a weakly-supervised to fully-supervised framework for object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00103"},{"key":"39_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20870-7_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T11:53:48Z","timestamp":1633434828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20870-7_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208691","9783030208707"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20870-7_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 May 2019","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.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":"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":"979","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":"274","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","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":"2.7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}