{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:25:02Z","timestamp":1784139902620,"version":"3.55.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","type":"electronic"}],"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\/978-3-030-58565-5_10","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"153-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":318,"title":["Fine-Grained Visual Classification via Progressive Multi-granularity Training of Jigsaw Patches"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8372-5637","authenticated-orcid":false,"given":"Ruoyi","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4081-3001","authenticated-orcid":false,"given":"Dongliang","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7928-7646","authenticated-orcid":false,"given":"Ayan Kumar","family":"Bhunia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3659-9476","authenticated-orcid":false,"given":"Jiyang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5908-3275","authenticated-orcid":false,"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, N., Kang, B., Sohn, K.A.: Image super-resolution via progressive cascading residual network. In: CVPR Workshops (2018)","DOI":"10.1109\/CVPRW.2018.00123"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Berg, T., Belhumeur, P.: Poof: part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.128"},{"key":"10_CR3","doi-asserted-by":"publisher","first-page":"4683","DOI":"10.1109\/TIP.2020.2973812","volume":"29","author":"D Chang","year":"2020","unstructured":"Chang, D., et al.: The devil is in the channels: mutual-channel loss for fine-grained image classification. IEEE Trans. Image Process. 29, 4683\u20134695 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., Mei, T.: Destruction and construction learning for fine-grained image recognition. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00530"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Fu, Y., Chen, K., Jiang, Y.G.: Image block augmentation for one-shot learning. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33013379"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Cho, T.S., Avidan, S., Freeman, W.T.: A probabilistic image jigsaw puzzle solver. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540212"},{"key":"10_CR7","unstructured":"Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Cui, Y., Zhou, F., Wang, J., Liu, X., Lin, Y., Belongie, S.: Kernel pooling for convolutional neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.325"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Ding, Y., Zhou, Y., Zhu, Y., Ye, Q., Jiao, J.: Selective sparse sampling for fine-grained image recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00670"},{"key":"10_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5","volume-title":"Computer Vision - ECCV 2018","author":"A Dubey","year":"2018","unstructured":"Dubey, A., Gupta, O., Guo, P., Raskar, R., Farrell, R., Naik, N.: Pairwise confusion for fine-grained visual classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_5"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Ge, W., Lin, X., Yu, Y.: Weakly supervised complementary parts models for fine-grained image classification from the bottom up. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00315"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Huang, S., Xu, Z., Tao, D., Zhang, Y.: Part-stacked CNN for fine-grained visual categorization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.132"},{"key":"10_CR17","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"10_CR18","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: ICCV Workshops (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"3","key":"10_CR21","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1109\/TCSVT.2016.2617332","volume":"28","author":"J Lei","year":"2016","unstructured":"Lei, J., Duan, J., Wu, F., Ling, N., Hou, C.: Fast mode decision based on grayscale similarity and inter-view correlation for depth map coding in 3D-HEVC. IEEE Trans. Circ. Syst. Video Technol. 28(3), 706\u2013718 (2016)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"5","key":"10_CR22","doi-asserted-by":"publisher","first-page":"4204","DOI":"10.1109\/TVT.2019.2895651","volume":"68","author":"X Li","year":"2019","unstructured":"Li, X., Yu, L., Chang, D., Ma, Z., Cao, J.: Dual cross-entropy loss for small-sample fine-grained vehicle classification. IEEE Trans. Veh. Technol. 68(5), 4204\u20134212 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"10_CR24","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Luo, W., et al.: Cross-X learning for fine-grained visual categorization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00833"},{"issue":"4","key":"10_CR26","doi-asserted-by":"publisher","first-page":"3224","DOI":"10.1109\/TVT.2019.2899972","volume":"68","author":"Z Ma","year":"2019","unstructured":"Ma, Z., et al.: Fine-grained vehicle classification with channel max pooling modified CNNs. IEEE Trans. Veh. Technol. 68(4), 3224\u20133233 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10_CR27","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"10_CR28","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Shaham, T.R., Dekel, T., Michaeli, T.: Singan: Learning a generative model from a single natural image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00467"},{"key":"10_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"10_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/978-3-319-10599-4_3","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K Son","year":"2014","unstructured":"Son, K., Hays, J., Cooper, D.B.: Solving square jigsaw puzzles with loop constraints. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 32\u201346. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_3"},{"key":"10_CR32","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Morariu, V.I., Davis, L.S.: Learning a discriminative filter bank within a CNN for fine-grained recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00436"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Perazzi, F., McWilliams, B., Sorkine-Hornung, A., Sorkine-Hornung, O., Schroers, C.: A fully progressive approach to single-image super-resolution. In: CVPR Workshops (2018)","DOI":"10.1109\/CVPRW.2018.00131"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: Iterative reorganization with weak spatial constraints: solving arbitrary jigsaw puzzles for unsupervised representation learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00201"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Wei, K., Yang, M., Wang, H., Deng, C., Liu, X.: Adversarial fine-grained composition learning for unseen attribute-object recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00384"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Xie, L., Tian, Q., Hong, R., Yan, S., Zhang, B.: Hierarchical part matching for fine-grained visual categorization. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.206"},{"key":"10_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-030-01264-9_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Yang","year":"2018","unstructured":"Yang, Z., Luo, T., Wang, D., Hu, Z., Gao, J., Wang, L.: Learning to navigate for fine-grained classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 438\u2013454. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_26"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, L., Huang, S., Liu, W., Tao, D.: Learning a mixture of granularity-specific experts for fine-grained categorization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00842"},{"key":"10_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_54"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.557"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Chang, D., Xie, J., Ma, Z.: IU-Module: intersection and union module for fine-grained visual classification. In: ICME (2020)","DOI":"10.1109\/ICME46284.2020.9102839"}],"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\/978-3-030-58565-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:04:23Z","timestamp":1731283463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 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.","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)"}}]}}