{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:42:28Z","timestamp":1784216548230,"version":"3.55.0"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"1s","license":[{"start":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Key Research and Development Program of Shandong Province to Dianmin Sun","award":["2019JZZY011101"],"award-info":[{"award-number":["2019JZZY011101"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076016 and 61876015"],"award-info":[{"award-number":["62076016 and 61876015"]}],"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":[[2022,2,28]]},"abstract":"<jats:p>\n            Person re-identification (Re-ID) has been promoted by the significant success of convolutional neural networks (CNNs). However, the application of such CNN-based Re-ID methods depends on the tremendous consumption of computation and memory resources, which affects its development on resource-limited devices such as next generation AI chips. As a result, CNN binarization has attracted increasing attention, which leads to binary neural networks (BNNs). In this article, we propose a new BNN-based framework for efficient person Re-ID (BiRe-ID). In this work, we discover that the significant performance drop of binarized models for Re-ID task is caused by the degraded representation capacity of kernels and features. To address the issues, we propose the\n            <jats:italic>kernel and feature refinement based on generative adversarial learning<\/jats:italic>\n            (KR-GAL and FR-GAL) to enhance the representation capacity of BNNs. We first introduce an adversarial attention mechanism to refine the binarized kernels based on their real-valued counterparts. Specifically, we introduce a scale factor to restore the scale of 1-bit convolution. And we employ an effective generative adversarial learning method to train the attention-aware scale factor. Furthermore, we introduce a self-supervised generative adversarial network to refine the low-level features using the corresponding high-level semantic information. Extensive experiments demonstrate that our BiRe-ID can be effectively implemented on various mainstream backbones for the Re-ID task. In terms of the performance, our BiRe-ID surpasses existing binarization methods by significant margins, at the level even comparable with the real-valued counterparts. For example, on Market-1501, BiRe-ID achieves 64.0% mAP on ResNet-18 backbone, with an impressive 12.51\u00d7 speedup in theory and 11.75\u00d7 storage saving. In particular, the KR-GAL and FR-GAL methods show strong generalization on multiple tasks such as Re-ID, image classification, object detection, and 3D point cloud processing.\n          <\/jats:p>","DOI":"10.1145\/3473340","type":"journal-article","created":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T12:05:50Z","timestamp":1644321950000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["BiRe-ID: Binary Neural Network for Efficient Person Re-ID"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7742-275X","authenticated-orcid":false,"given":"Sheng","family":"Xu","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, China; Shenzhen Academy of Aerospace Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhu","family":"L\u00fc","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, China; State Key Laboratory of Software Development Environment, Beihang University, China; Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Deep Learning, Baidu Research, China; National Engineering Laboratory for Deep Learning Technology and Application, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Doermann","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305404"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"e_1_3_2_4_2","first-page":"189","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Bak Slawomir","year":"2018","unstructured":"Slawomir Bak, Peter Carr, and Jean-Francois Lalonde. 2018. Domain adaptation through synthesis for unsupervised person re-identification. In Proceedings of the European Conference on Computer Vision. 189\u2013205."},{"key":"e_1_3_2_5_2","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang Angel X.","year":"2015","unstructured":"Angel X. Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et\u00a0al. 2015. ShapeNet: An information-rich 3D model repository. arXiv preprint arXiv:1512.03012.","journal-title":"arXiv preprint arXiv:1512.03012"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969588"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999852"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327056"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018344"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00501"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295327"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304889.3304970"},{"key":"e_1_3_2_20_2","article-title":"IAUnet: Global context-aware feature learning for person reidentification","author":"Hou Ruibing","year":"2020","unstructured":"Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, and Xilin Chen. 2020. IAUnet: Global context-aware feature learning for person reidentification. IEEE Trans. Neural Netw. Learn. Syst. 32, 10 (2020).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2874715"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.456"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00117"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/109230.109298"},{"key":"e_1_3_2_28_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Li Hao","year":"2017","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2017. Pruning filters for efficient ConvNets. In Proceedings of the International Conference on Learning Representations. 1\u201313."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172193"},{"key":"e_1_3_2_31_2","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Lin Mingbao","year":"2020","unstructured":"Mingbao Lin, Rongrong Ji, Zihan Xu, Baochang Zhang, Yan Wang, Yongjian Wu, Feiyue Huang, and Chia-Wen Lin. 2020. Rotated binary neural network. In Proceedings of the Conference on Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298447"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294804"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367032.3367154"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_9"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"e_1_3_2_40_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Martinez Brais","year":"2020","unstructured":"Brais Martinez, Jing Yang, Adrian Bulat, and Georgios Tzimiropoulos. 2020. Training binary neural networks with real-to-binary convolutions. In Proceedings of the International Conference on Learning Representations. 1\u201311."},{"key":"e_1_3_2_41_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"McDonnell Mark D.","year":"2018","unstructured":"Mark D. McDonnell. 2018. Training wide residual networks for deployment using a single bit for each weight. In Proceedings of the International Conference on Learning Representations. 1\u201316."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305954"},{"key":"e_1_3_2_43_2","first-page":"652","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi Charles R.","year":"2017","unstructured":"Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652\u2013660."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295263"},{"key":"e_1_3_2_45_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Qin Haotong","year":"2020","unstructured":"Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Liu, and Hao Su. 2020. BiPointNet: Binary neural network for point clouds. In Proceedings of the International Conference on Learning Representations. 1\u201324."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00632"},{"key":"e_1_3_2_50_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for thin deep nets. In Proceedings of the International Conference on Learning Representations. 1\u201313."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.427"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_30"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_25"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327493"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_20"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00242"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00094"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00212"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877886"},{"key":"e_1_3_2_64_2","first-page":"1912","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1912\u20131920."},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3020648"},{"key":"e_1_3_2_66_2","first-page":"1","article-title":"Efficient structured pruning based on deep feature stabilization","author":"Xu Sheng","year":"2021","unstructured":"Sheng Xu, Hanlin Chen, Xuan Gong, Kexin Liu, Jinhu L\u00fc, and Baochang Zhang. 2021. Efficient structured pruning based on deep feature stabilization. Neural Comput. Applic. 33 (2021), 1\u201312.","journal-title":"Neural Comput. Applic."},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.23919\/CCC50068.2020.9189610"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410338.3412340"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00563"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.16"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"},{"key":"e_1_3_2_72_2","article-title":"VehicleNet: Learning robust visual representation for vehicle re-identification","author":"Zheng Zhedong","year":"2020","unstructured":"Zhedong Zheng, Tao Ruan, Yunchao Wei, Yi Yang, and Tao Mei. 2020. VehicleNet: Learning robust visual representation for vehicle re-identification. IEEE Trans. Multimedia. 23 (2020).","journal-title":"IEEE Trans. Multimedia"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00224"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3159171"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_11"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00069"},{"key":"e_1_3_2_78_2","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160.","journal-title":"arXiv preprint arXiv:1606.06160"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3473340","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3473340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:15Z","timestamp":1750195695000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3473340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,8]]},"references-count":78,"journal-issue":{"issue":"1s","published-print":{"date-parts":[[2022,2,28]]}},"alternative-id":["10.1145\/3473340"],"URL":"https:\/\/doi.org\/10.1145\/3473340","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,8]]},"assertion":[{"value":"2021-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}