{"type":"ScholarlyArticle","title":"Disentangled Feature Learning Network for Vehicle Re-Identification","authors":[{"name":"Yan Bai","slug":"yan-bai","given":"Yan","family":"Bai","affiliation":"National Engineering Lab for Video Technology , Peking University , Beijing , China; Peng Cheng Laboratory , Shenzhen , China"},{"name":"Yihang Lou","slug":"yihang-lou","given":"Yihang","family":"Lou","affiliation":"National Engineering Lab for Video Technology , Peking University , Beijing , China; Peng Cheng Laboratory , Shenzhen , China"},{"name":"Yongxing Dai","slug":"yongxing-dai","given":"Yongxing","family":"Dai","affiliation":"National Engineering Lab for Video Technology , Peking University , Beijing , China; Peng Cheng Laboratory , Shenzhen , China"},{"name":"Jun Liu","slug":"jun-liu","given":"Jun","family":"Liu","affiliation":"ISTD Pillar , Singapore University of Technology and Design , Singapore"},{"name":"Ziqian Chen","slug":"ziqian-chen","given":"Ziqian","family":"Chen","affiliation":"National Engineering Lab for Video Technology , Peking University , Beijing , China; Peng Cheng Laboratory , Shenzhen , China"},{"name":"Ling-Yu Duan","slug":"ling-yu-duan","given":"Ling-Yu","family":"Duan","affiliation":"National Engineering Lab for Video Technology , Peking University , Beijing , China; Peng Cheng Laboratory , Shenzhen , China"}],"abstract":"Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the same vehicle. However, these two characteristics are hard to be  encapsulated into a single feature representation simultaneously with unified supervision. Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific  and  common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the consistency of the metric scales. The experiments show the effectiveness of our method that achieves state-of-the-art performance on three challenging datasets.","doi":"10.24963/ijcai.2020/66","url":"https://ijcai.org/proceedings/2020/66","pdf":"https://ijcai.org/proceedings/2020/0066.pdf","markdown":"https://ijcai.org/proceedings/2020/66.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/66","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Computer Vision","track":"Main track","number":66,"pages":{"first":474,"last":480},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Computer Vision: Perception"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24058/file_24058.m3u8","length_sec":296,"provider":"hls"}],"references":[{"position":1,"raw":"[Alfasly et al., 2019] Saghir Alfasly, Yongjian Hu, Haoliang Li, Tiancai Liang, Xiaofeng Jin, Beibei Liu, and Qingli Zhao. Multi-label-based similarity learning for vehicle re- identification. IEEE Access, 7:162605-162616, 2019.","title":"Multi-label-based similarity learning for vehicle reidentification","authors":"Saghir Alfasly, Yongjian Hu, Haoliang Li, Tiancai Liang, Xiaofeng Jin, Beibei Liu, Qingli Zhao","year":"2019","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bahdanau et al., 2014] Dzmitry Bahdanau, Kyunghyun Cho, and et al. Neural machine translation by jointly learning to align and translate. Computer Science, 2014.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bai et al., 2018] Yan Bai, Yihang Lou, and et al. Group sen- sitive triplet embedding for vehicle re-identification. IEEE Transactions on Multimedia, 2018.","title":"Group sensitive triplet embedding for vehicle re-identification","authors":"Yan Bai, Yihang Lou","year":"2018","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bulan et al., 2017] Orhan Bulan, Vladimir Kozitsky, Pal- ghat Ramesh, and Matthew Shreve. Segmentation-and annotation-free license plate recognition with deep local- ization and failure identification. IEEE Transactions on In- telligent Transportation Systems, 18(9):2351-2363, 2017.","title":"Segmentation-and annotation-free license plate recognition with deep localization and failure identification","authors":"Orhan Bulan, Vladimir Kozitsky, Palghat Ramesh, Matthew Shreve","year":"2017","venue":"IEEE Transactions on Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chu et al., 2019] Ruihang Chu, Yifan Sun, Yadong Li, Zheng Liu, and et al. Vehicle re-identification with viewpoint-aware metric learning. In IEEE International Conference on Computer Vision, pages 8282-8291, 2019.","title":"Vehicle re-identification with viewpoint-aware metric learning","authors":"Chu","year":"2019","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2019] Bing He, Jia Li, Yifan Zhao, and Yonghong Tian. Part-regularized near-duplicate vehicle re-identification. In IEEE Conference on Computer Vision and Pattern Recognition, pages 3997-4005, 2019.","title":"Part-regularized near-duplicate vehicle re-identification","authors":"He","year":"2019","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hermans et al., 2017] Alexander Hermans, Lucas Beyer, and Bastian Leibe. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017.","title":"In defense of the triplet loss for person re-identification","authors":"Alexander Hermans, Lucas Beyer, Bastian Leibe","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2016a] Hongye Liu, Yonghong Tian, and et al. Deep relative distance learning: Tell the difference be- tween similar vehicles. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2167-2175, 2016.","title":"Deep relative distance learning: Tell the difference between similar vehicles","authors":"Liu","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Liu et al., 2016b] Xinchen Liu, Wu Liu, Huadong Ma, and Huiyuan Fu. Large-scale vehicle re-identification in urban surveillance videos. In IEEE International Conference on Multimedia and Expo, 2016, pages 1-6. IEEE, 2016.","title":"Large-scale vehicle re-identification in urban surveillance videos","authors":"Liu","year":"2016","venue":"IEEE International Conference on Multimedia and Expo","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2016c] Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. A deep learning-based approach to pro- gressive vehicle re-identification for urban surveillance. In IEEE International Conference on European Conference on Computer Vision, pages 869-884. Springer, 2016.","title":"A deep learning-based approach to progressive vehicle re-identification for urban surveillance","authors":"Liu","year":"2016","venue":"IEEE International Conference on European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lou et al., 2019a] Yihang Lou, Yan Bai, and et al. Em- bedding adversarial learning for vehicle re-identification. IEEE Transactions on Image Processing, 2019.","title":"Embedding adversarial learning for vehicle re-identification","authors":"Lou","year":"2019","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lou et al., 2019b] Yihang Lou, Yan Bai, and et al. Veri- wild: A large dataset and a new method for vehicle re- identification in the wild. In IEEE Conference on Com- puter Vision and Pattern Recognition, pages 3235-3243, 2019.","title":"Veriwild: A large dataset and a new method for vehicle reidentification in the wild","authors":"Lou","year":"2019","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ma et al., 2017] Liqian Ma, Qianru Sun, and et al. Dis- entangled person image generation. arXiv preprint arXiv:1712.02621, 2017.","title":"Liqian Ma, Qianru Sun, and et al. Disentangled person image generation","authors":"Ma","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pirazh et al., 2019] Khorramshahi Pirazh, Amit Kumar, Neehar Peri, and et al. A dual path modelwith adaptive attention for vehicle re-identification. IEEE International Conference on Computer Vision, 2019.","title":"A dual path modelwith adaptive attention for vehicle re-identification","authors":"Pirazh","year":"2019","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Rivlin, 1974] Theodore J Rivlin. The Chebyshev polynomi- als. Wiley, 1974.","title":"The Chebyshev polynomials","authors":"Theodore J Rivlin","year":"1974","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sandler et al., 2018] Mark Sandler, Andrew Howard, and et al. Mobilenetv2: Inverted residuals and linear bottle- necks. In IEEE conference on computer vision and pattern recognition, pages 4510-4520, 2018.","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","authors":"Mark Sandler, Andrew Howard","year":"2018","venue":"IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Schroff et al., 2015a] Florian Schroff, Kalenichenko Dmitry, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In Computer Vision and Pattern Recognition, pages 815-823, 2015.","title":"Facenet: A unified embedding for face recognition and clustering","authors":"Schroff","year":"2015","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schroff et al., 2015b] Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A uni- fied embedding for face recognition and clustering. In IEEE Conference on Computer Vision and Pattern Recognition, pages 815-823, 2015.","title":"Facenet: A unified embedding for face recognition and clustering","authors":"Schroff","year":"2015","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Szegedy et al., 2016] Christian Szegedy, Vincent Van- houcke, and et al. Rethinking the inception architecture for computer vision. In the IEEE conference on computer vision and pattern recognition, pages 2818-2826, 2016.","title":"Rethinking the inception architecture for computer vision","authors":"Szegedy","year":"2016","venue":"the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tang et al., 2019] Zheng Tang, Milind Naphade, and et al. Pamtri: Pose-aware multi-task learning for vehicle re- identification using highly randomized synthetic data. In IEEE International Conference on Computer Vision, pages 211-220, 2019.","title":"Pamtri: Pose-aware multi-task learning for vehicle reidentification using highly randomized synthetic data","authors":"Zheng Tang, Milind Naphade","year":"2019","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tran et al., 2017] Luan Tran, Xi Yin, and et al. Disentan- gled representation learning gan for pose-invariant face recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1415-1424, 2017.","title":"Disentangled representation learning gan for pose-invariant face recognition","authors":"Luan Tran, Xi Yin","year":"2017","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2017] Zhongdao Wang, Luming Tang, and et al. Orientation invariant feature embedding and spa- tial temporal regularization for vehicle re-identification. In IEEE International Conference on Computer Vision, pages 379-387, 2017.","title":"Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification","authors":"Wang","year":"2017","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wei et al., 2018] Xiu-Shen Wei, Chen-Lin Zhang, and et al. Coarse-to-fine: A rnn-based hierarchical attention model for vehicle re-identification. In Asian Conference on Com- puter Vision, pages 575-591. Springer, 2018.","title":"Coarse-to-fine: A rnn-based hierarchical attention model for vehicle re-identification","authors":"Xiu-Shen Wei, Chen-Lin Zhang","year":"2018","venue":"Asian Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xu et al., 2015] Kelvin Xu, Jimmy Ba, and et al. Show, at- tend and tell: Neural image caption generation with visual attention. Computer Science, pages 2048-2057, 2015.","title":"Show, attend and tell: Neural image caption generation with visual attention","authors":"Kelvin Xu, Jimmy Ba","year":"2015","venue":"Computer Science","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yuan et al., 2016] Yuhui Yuan, Kuiyuan Yang, and Chao Zhang. Hard-aware deeply cascaded embedding. arXiv preprint arXiv:1611.05720, 2016.","title":"Hard-aware deeply cascaded embedding","authors":"Yuhui Yuan, Kuiyuan Yang, Chao Zhang","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2019] Yiru Zhao, Xu Shen, and et al. Attribute- driven feature disentangling and temporal aggregation for video person re-identification. In IEEE Conference on Computer Vision and Pattern Recognition, 2019.","title":"Attributedriven feature disentangling and temporal aggregation for video person re-identification","authors":"Zhao","year":"2019","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou and Shao, 2018] Yi Zhou and Ling Shao. View- point aware attentive multi-view inference for vehicle re- identification. In IEEE Conference on Computer Vision and Pattern Recognition, pages 6489-6498, 2018.","title":"Viewpoint aware attentive multi-view inference for vehicle reidentification","authors":"Shao ; ] Yi Zhou, Ling Zhou, Shao","year":"2018","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}