{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T03:36:12Z","timestamp":1776051372519,"version":"3.50.1"},"reference-count":75,"publisher":"Association for Computing Machinery (ACM)","issue":"1s","license":[{"start":{"date-parts":[[2021,1,31]],"date-time":"2021-01-31T00:00:00Z","timestamp":1612051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of Chain","doi-asserted-by":"crossref","award":["61827901 and 62076016"],"award-info":[{"award-number":["61827901 and 62076016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,1,31]]},"abstract":"<jats:p>Fine-grained visual categorization (FGVC) aims to automatically recognize objects from different sub-ordinate categories. Despite attracting considerable attention from both academia and industry, it remains a challenging task due to subtle visual differences among different classes. Cross-layer feature aggregation and cross-image pairwise learning become prevailing in improving the performance of FGVC by extracting discriminative class-specific features. However, they are still inefficient to fully use the cross-layer information based on the simple aggregation strategy, while existing pairwise learning methods also fail to explore long-range interactions between different images. To address these problems, we propose a novel Alignment Enhancement Network (AENet), including two-level alignments, Cross-layer Alignment (CLA) and Cross-image Alignment (CIA). The CLA module exploits the cross-layer relationship between low-level spatial information and high-level semantic information, which contributes to cross-layer feature aggregation to improve the capacity of feature representation for input images. The new CIA module is further introduced to produce the aligned feature map, which can enhance the relevant information as well as suppress the irrelevant information across the whole spatial region. Our method is based on an underlying assumption that the aligned feature map should be closer to the inputs of CIA when they belong to the same category. Accordingly, we establish Semantic Affinity Loss to supervise the feature alignment within each CIA block. Experimental results on four challenging datasets show that the proposed AENet achieves the state-of-the-art results over prior arts.<\/jats:p>","DOI":"10.1145\/3446208","type":"journal-article","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T01:53:55Z","timestamp":1617242035000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Alignment Enhancement Network for Fine-grained Visual Categorization"],"prefix":"10.1145","volume":"17","author":[{"given":"Yutao","family":"Hu","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuhui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Computer Science Department, Aberystwyth University, SY23 3FL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianbin","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, China; National Engineering Laboratory of Big Data Application Technologies on Comprehensive Transportation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,3,31]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Serge Belongie, and Pietro Perona.","author":"Branson Steve","year":"2014","unstructured":"Steve Branson , Grant Van Horn , Serge Belongie, and Pietro Perona. 2014 . Bird species categorization using pose normalized deep convolutional nets. Retrieved from https:\/\/arXiv:1406.2952. Steve Branson, Grant Van Horn, Serge Belongie, and Pietro Perona. 2014. Bird species categorization using pose normalized deep convolutional nets. Retrieved from https:\/\/arXiv:1406.2952."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.63"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927224"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3231742"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902115"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.10.054"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.095"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_38"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Zhang Fan Li Meng Zhai Guisheng and Liu Yizhao. 2020. Multi-branch and multi-scale attention learning for fine-grained visual categorization. Retrieved from https:\/\/arXiv:2003.09150.  Zhang Fan Li Meng Zhai Guisheng and Liu Yizhao. 2020. Multi-branch and multi-scale attention learning for fine-grained visual categorization. Retrieved from https:\/\/arXiv:2003.09150.","DOI":"10.1007\/978-3-030-67832-6_12"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377876"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.02.017"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294775"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00335"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093601"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852022"},{"key":"e_1_2_1_26_1","unstructured":"Yutao Hu Xiaolong Jiang Xuhui Liu Baochang Zhang Jungong Han Xianbin Cao and David Doermann. 2020. NAS-Count: Counting-by-density with neural architecture search. Retrieved from https:\/\/arXiv:2003.00217.  Yutao Hu Xiaolong Jiang Xuhui Liu Baochang Zhang Jungong Han Xianbin Cao and David Doermann. 2020. NAS-Count: Counting-by-density with neural architecture search. Retrieved from https:\/\/arXiv:2003.00217."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978115"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"e_1_2_1_29_1","volume-title":"et\u00a0al","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang , Youlong Cheng , Ankur Bapna , Orhan Firat , Dehao Chen , Mia Chen , HyoukJoong Lee , Jiquan Ngiam , Quoc V. Le , Yonghui Wu , et\u00a0al . 2019 . Gpipe : Efficient training of giant neural networks using pipeline parallelism. In Advances in Neural Information Processing Systems. MIT Press , 103\u2013112. Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, et\u00a0al. 2019. Gpipe: Efficient training of giant neural networks using pipeline parallelism. In Advances in Neural Information Processing Systems. MIT Press, 103\u2013112."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00629"},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC\u201911)","volume":"2","author":"Khosla Aditya","year":"2011","unstructured":"Aditya Khosla , Nityananda Jayadevaprakash , Bangpeng Yao , and Fei-Fei Li . 2011 . Novel dataset for fine-grained image categorization: Stanford dogs . In Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC\u201911) , Vol. 2 . Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Fei-Fei Li. 2011. Novel dataset for fine-grained image categorization: Stanford dogs. In Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC\u201911), Vol. 2."},{"key":"e_1_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Dimitri Korsch Paul Bodesheim and Joachim Denzler. 2020. End-to-end learning of a fisher vector encoding for part features in fine-grained recognition. Retrieved from https:\/\/arXiv:2007.02080.  Dimitri Korsch Paul Bodesheim and Joachim Denzler. 2020. End-to-end learning of a fisher vector encoding for part features in fine-grained recognition. Retrieved from https:\/\/arXiv:2007.02080.","DOI":"10.1007\/978-3-030-92659-5_9"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Hao Li Xiaopeng Zhang Hongkai Xiong and Qi Tian. 2020. Attribute mix: Semantic data augmentation for fine grained recognition. Retrieved from https:\/\/arXiv:2004.02684.  Hao Li Xiaopeng Zhang Hongkai Xiong and Qi Tian. 2020. Attribute mix: Semantic data augmentation for fine grained recognition. Retrieved from https:\/\/arXiv:2004.02684.","DOI":"10.1109\/VCIP49819.2020.9301763"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240579"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"e_1_2_1_39_1","unstructured":"Tsung-Yu Lin and Subhransu Maji. 2017. Improved bilinear pooling with CNNs. Retrieved from https:\/\/arXiv:1707.06772.  Tsung-Yu Lin and Subhransu Maji. 2017. Improved bilinear pooling with CNNs. Retrieved from https:\/\/arXiv:1707.06772."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_2_1_41_1","volume-title":"Berg","author":"Liu Wei","year":"2016","unstructured":"Wei Liu , Dragomir Anguelov , Dumitru Erhan , Christian Szegedy , Scott Reed , Cheng-Yang Fu , and Alexander C . Berg . 2016 . SSD : Single shot multibox detector. In Proceedings of the European Conference on Computer Vision. Springer , 21\u201337. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision. Springer, 21\u201337."},{"key":"e_1_2_1_42_1","volume-title":"Fully convolutional attention localization networks: Efficient attention localization for fine-grained recognition. arXiv preprint arXiv:1603.06765","author":"Liu Xiao","year":"2016","unstructured":"Xiao Liu , Tian Xia , Jiang Wang , and Yuanqing Lin . 2016. Fully convolutional attention localization networks: Efficient attention localization for fine-grained recognition. arXiv preprint arXiv:1603.06765 ( 2016 ). Xiao Liu, Tian Xia, Jiang Wang, and Yuanqing Lin. 2016. Fully convolutional attention localization networks: Efficient attention localization for fine-grained recognition. arXiv preprint arXiv:1603.06765 (2016)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2835143"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107676"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350870"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366567"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_1_50_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. Retrieved from https:\/\/arXiv:1409.1556.  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. Retrieved from https:\/\/arXiv:1409.1556."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"e_1_2_1_52_1","volume-title":"Le","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V . Le . 2019 . Efficientnet : Rethinking model scaling for convolutional neural networks. Retrieved from https:\/\/arXiv:1905.11946. Mingxing Tan and Quoc V. Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. Retrieved from https:\/\/arXiv:1905.11946."},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209666"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.276"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107448"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.689"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_1_61_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1163\u20131172","author":"Wang Yaming","unstructured":"Yaming Wang , Jonghyun Choi , Vlad Morariu , and Larry S. Davis . 2016. Mining discriminative triplets of patches for fine-grained classification . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1163\u20131172 . Yaming Wang, Jonghyun Choi, Vlad Morariu, and Larry S. Davis. 2016. Mining discriminative triplets of patches for fine-grained classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1163\u20131172."},{"key":"e_1_2_1_62_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4148\u20134157","author":"Wang Yaming","unstructured":"Yaming Wang , Vlad I. Morariu , and Larry S. Davis . 2018. Learning a discriminative filter bank within a CNN for fine-grained recognition . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4148\u20134157 . Yaming Wang, Vlad I. Morariu, and Larry S. Davis. 2018. Learning a discriminative filter bank within a CNN for fine-grained recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4148\u20134157."},{"key":"e_1_2_1_63_1","unstructured":"P. Welinder S. Branson C. Wah F. Schroff S. Belongie and P. Perona. 2010. Caltech-UCSD birds 200. Technical Report California Institute of Technology.  P. Welinder S. Branson C. Wah F. Schroff S. Belongie and P. Perona. 2010. Caltech-UCSD birds 200. Technical Report California Institute of Technology."},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307363.3307382"},{"key":"e_1_2_1_65_1","volume-title":"Proceedings of the European Conference on Computer Vision. Springer, 247\u2013263","author":"Xiang Liuyu","year":"2020","unstructured":"Liuyu Xiang , Guiguang Ding , and Jungong Han . 2020 . Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification . In Proceedings of the European Conference on Computer Vision. Springer, 247\u2013263 . Liuyu Xiang, Guiguang Ding, and Jungong Han. 2020. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In Proceedings of the European Conference on Computer Vision. Springer, 247\u2013263."},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356019"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"e_1_2_1_73_1","volume-title":"Advances in Neural Information Processing Systems","author":"Zheng Heliang","unstructured":"Heliang Zheng , Jianlong Fu , Zheng-Jun Zha , and Jiebo Luo . 2019. Learning deep bilinear transformation for fine-grained image representation . In Advances in Neural Information Processing Systems . MIT Press , 4279\u20134288. Heliang Zheng, Jianlong Fu, Zheng-Jun Zha, and Jiebo Luo. 2019. Learning deep bilinear transformation for fine-grained image representation. In Advances in Neural Information Processing Systems. MIT Press, 4279\u20134288."},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3446208","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3446208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:04Z","timestamp":1750193224000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3446208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,31]]},"references-count":75,"journal-issue":{"issue":"1s","published-print":{"date-parts":[[2021,1,31]]}},"alternative-id":["10.1145\/3446208"],"URL":"https:\/\/doi.org\/10.1145\/3446208","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,31]]},"assertion":[{"value":"2020-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-12-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}