{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T03:14:55Z","timestamp":1762053295649,"version":"build-2065373602"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T00:00:00Z","timestamp":1654128000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T00:00:00Z","timestamp":1654128000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s00371-022-02481-7","type":"journal-article","created":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T20:02:26Z","timestamp":1654200146000},"page":"2597-2608","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Inverse transformation sampling-based attentive cutout for fine-grained visual recognition"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2230-8511","authenticated-orcid":false,"given":"Chen","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaojin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiyan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfeng","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,2]]},"reference":[{"key":"2481_CR1","doi-asserted-by":"crossref","unstructured":"Berg, T., Belhumeur, P.N.: Poof: Part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 955\u2013962 (2013)","DOI":"10.1109\/CVPR.2013.128"},{"key":"2481_CR2","doi-asserted-by":"crossref","unstructured":"Cai, S., Zuo, W., Zhang, L.: Higher-order integration of hierarchical convolutional activations for fine-grained visual categorization. In: Proceedings of the IEEE Conference on Computer Vision, pp. 511\u2013520 (2017)","DOI":"10.1109\/ICCV.2017.63"},{"key":"2481_CR3","doi-asserted-by":"crossref","unstructured":"Chai, Y., Lempitsky, V., Zisserman, A.: Symbiotic segmentation and part localization for fine-grained categorization. In: Proceedings of the International Conference on Computer Vision, pp. 321\u2013328 (2013)","DOI":"10.1109\/ICCV.2013.47"},{"key":"2481_CR4","doi-asserted-by":"publisher","first-page":"4683","DOI":"10.1109\/TIP.2020.2973812","volume":"29","author":"D Chang","year":"2020","unstructured":"Chang, D., Ding, Y., Xie, J., Bhunia, A.K., Li, X., Ma, Z., Wu, M., Guo, J., Song, Y.Z.: 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":"2481_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., Mei, T.: Destruction and construction learning for fine-grained image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5157\u20135166 (2019)","DOI":"10.1109\/CVPR.2019.00530"},{"key":"2481_CR6","doi-asserted-by":"crossref","unstructured":"Cui, Y., Zhou, F., Wang, J., Liu, X., Lin, Y., Belongie, S.: Kernel pooling for convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3049\u20133058 (2017)","DOI":"10.1109\/CVPR.2017.325"},{"key":"2481_CR7","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout (2017). arXiv preprint arXiv:1708.04552"},{"key":"2481_CR8","doi-asserted-by":"crossref","unstructured":"Devroye, L.: Sample-based non-uniform random variate generation. In: Proceedings of the Conference on Winter Simulation, pp. 260\u2013265 (1986)","DOI":"10.1007\/978-1-4613-8643-8"},{"key":"2481_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: Proceedings of the IEEE Conference on Computer Vision, pp. 6598\u20136607 (2019)","DOI":"10.1109\/ICCV.2019.00670"},{"key":"2481_CR10","doi-asserted-by":"crossref","unstructured":"Dubey, A., Gupta, O., Guo, P., Raskar, R., Farrell, R., Naik, N.: Pairwise confusion for fine-grained visual classification. In: Proceedings of the IEEE European Conference on Computer Vision, pp. 70\u201386 (2018)","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"2481_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4476\u20134484 (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"2481_CR12","doi-asserted-by":"crossref","unstructured":"Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 317\u2013326 (2016)","DOI":"10.1109\/CVPR.2016.41"},{"key":"2481_CR13","doi-asserted-by":"crossref","unstructured":"Gavves, E., Fernando, B., Snoek, C.G.M., Smeulders, A.W.M., Tuytelaars, T.: Fine-grained categorization by alignments. In: Proceedings of the IEEE Conference on International Conference on Computer Vision, pp. 1713\u20131720 (2013)","DOI":"10.1109\/ICCV.2013.215"},{"key":"2481_CR14","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3034\u20133043 (2019)","DOI":"10.1109\/CVPR.2019.00315"},{"key":"2481_CR15","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":"2481_CR16","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of The International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"2481_CR17","doi-asserted-by":"crossref","unstructured":"Kong, S., Fowlkes, C.: Low-rank bilinear pooling for fine-grained classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.743"},{"key":"2481_CR18","doi-asserted-by":"crossref","unstructured":"Krause, J., Jin, H., Yang, J., Fei-Fei, L.: Fine-grained recognition without part annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5546\u20135555 (2015)","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"2481_CR19","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"2481_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"2481_CR21","doi-asserted-by":"crossref","unstructured":"Lam, M., Mahasseni, B., Todorovic, S.: Fine-grained recognition as hsnet search for informative image parts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.688"},{"key":"2481_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear cnn models for fine-grained visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1449\u20131457 (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"2481_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Huang, L., Wei, Z., Zhang, W.: Subtler mixed attention network on fine-grained image classification. Appl. Intell. 1\u201314 (2021)","DOI":"10.1007\/s10489-021-02280-y"},{"key":"2481_CR24","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-Grained Visual Classification of Aircraft. Technical Report (2013). arXiv:1306.5151"},{"key":"2481_CR25","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Proceedings of the IEEE Indian Conference on Computer Vision, Graphics and Image Processing, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2481_CR26","doi-asserted-by":"publisher","first-page":"107947","DOI":"10.1016\/j.patcog.2021.107947","volume":"116","author":"Y Niu","year":"2021","unstructured":"Niu, Y., Jiao, Y., Shi, G.: Attention-shift based deep neural network for fine-grained visual categorization. Pattern Recogn. 116, 107947 (2021)","journal-title":"Pattern Recogn."},{"key":"2481_CR27","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"2481_CR28","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1109\/TIP.2017.2774041","volume":"27","author":"Y Peng","year":"2018","unstructured":"Peng, Y., He, X., Zhao, J.: Object-part attention model for fine-grained image classification. IEEE Trans. Image Process. 27, 1487\u20131500 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2481_CR29","doi-asserted-by":"crossref","unstructured":"Sedik, A., Hammad, M., Abd El-Samie, F.E., et al.: Efficient deep learning approach for augmented detection of Coronavirus disease. Neural Comput. Appl. 1\u201318 (2021)","DOI":"10.1007\/s00521-020-05410-8"},{"issue":"7","key":"2481_CR30","doi-asserted-by":"publisher","first-page":"769","DOI":"10.3390\/v12070769","volume":"12","author":"A Sedik","year":"2020","unstructured":"Sedik, A., Iliyasu, A.M., El-Rahiem, A., et al.: Deploying machine and deep learning models for efficient data-augmented detection of COVID-19 infections. Viruses 12(7), 769 (2020)","journal-title":"Viruses"},{"key":"2481_CR31","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"2481_CR32","doi-asserted-by":"crossref","unstructured":"Song, K., Wei, X., Shu, X., Song, R., Lu, J.: Bi-modal progressive mask attention for fine-grained recognition. IEEE Trans. Image Process. 1\u20131 (2020)","DOI":"10.1109\/TIP.2020.2996736"},{"key":"2481_CR33","doi-asserted-by":"crossref","unstructured":"Sun, G., Cholakkal, H., Khan, S., Khan, F.S., Shao, L.: Fine-grained recognition: accounting for subtle differences between similar classes. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12047\u201312054 (2020)","DOI":"10.1609\/aaai.v34i07.6882"},{"key":"2481_CR34","doi-asserted-by":"crossref","unstructured":"Tokozume, Y., Ushiku, Y., Harada, T.: Between-class learning for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5486\u20135494 (2018)","DOI":"10.1109\/CVPR.2018.00575"},{"key":"2481_CR35","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"2481_CR36","unstructured":"Verma, V., Lamb, A., Beckham, C., Najafi, A., Mitliagkas, I., Lopez-Paz, D., Bengio, Y.: Manifold mixup: better representations by interpolating hidden states. In: Proceedings of International Conference on Machine Learning, pp. 6438\u20136447 (2019)"},{"key":"2481_CR37","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset (2011)"},{"key":"2481_CR38","doi-asserted-by":"crossref","unstructured":"Walawalkar, D., Shen, Z., Liu, Z., et al.: Attentive CutMix: an enhanced data augmentation approach for deep learning based image classification. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (2020)","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"2481_CR39","doi-asserted-by":"crossref","unstructured":"Wang, D., Shen, Z., Shao, J., Zhang, W., Xue, X., Zhang, Z.: Multiple granularity descriptors for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2399\u20132406 (2015)","DOI":"10.1109\/ICCV.2015.276"},{"key":"2481_CR40","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4148\u20134157 (2018)","DOI":"10.1109\/CVPR.2018.00436"},{"key":"2481_CR41","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1016\/j.patcog.2017.10.002","volume":"76","author":"XS Wei","year":"2018","unstructured":"Wei, X.S., Xie, C.W., Wu, J., Shen, C.: Mask-cnn: localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recogn. 76, 704\u2013714 (2018)","journal-title":"Pattern Recogn."},{"key":"2481_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., Luo, T., Wang, D., Hu, Z., Gao, J., Wang, L.: Learning to navigate for fine-grained classification. In: Proceedings of the IEEE European Conference on Computer Vision, pp. 438\u2013454 (2018)","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"2481_CR43","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Chun, S., Oh, S.J., Yoo, Y., Choe, J.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2481_CR44","doi-asserted-by":"publisher","first-page":"108067","DOI":"10.1016\/j.patcog.2021.108067","volume":"119","author":"X Yu","year":"2021","unstructured":"Yu, X., Zhao, Y., Gao, Y., Xiong, S.: MaskCOV: a random mask covariance network for ultra-fine-grained visual categorization. Pattern Recogn. 119, 108067 (2021)","journal-title":"Pattern Recogn."},{"key":"2481_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: Proceedings of International Conference on Learning Representations (2017)","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"2481_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Elhoseiny, M., Huang, X., Zhang, S., Elgammal, A., Metaxas, D.: Spda-cnn: unifying semantic part detection and abstraction for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1143\u20131152 (2016)","DOI":"10.1109\/CVPR.2016.129"},{"key":"2481_CR47","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 8331\u20138340 (2019)","DOI":"10.1109\/ICCV.2019.00842"},{"key":"2481_CR48","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1109\/TIP.2016.2531289","volume":"25","author":"Y Zhang","year":"2016","unstructured":"Zhang, Y., Wei, X.S., Wu, J., Cai, J., Lu, J., Nguyen, V.A., Do, M.N.: Weakly supervised fine-grained categorization with part-based image representation. IEEE Trans. Image Process. 25, 1713\u20131725 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"2481_CR49","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: Proceedings of the International Conference on Computer Vision, pp. 5219\u20135227 (2017)","DOI":"10.1109\/ICCV.2017.557"},{"key":"2481_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J.: Looking for the devil in the details: learning trilinear attention sampling network for fine-grained image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5012\u20135021 (2019)","DOI":"10.1109\/CVPR.2019.00515"},{"key":"2481_CR51","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/TIP.2019.2921876","volume":"29","author":"H Zheng","year":"2020","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J., Mei, T.: Learning rich part hierarchies with progressive attention networks for fine-grained image recognition. IEEE Trans. Image Process. 29, 476\u2013488 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"2481_CR52","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"2481_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02481-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02481-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02481-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T10:14:26Z","timestamp":1688033666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02481-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,2]]},"references-count":53,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["2481"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02481-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2022,6,2]]},"assertion":[{"value":"13 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}