Abstract
The effective training of supervised Person Re-identification (Re-ID) models requires sufficient pairwise labeled data. However, when there is limited annotation resource, it is difficult to collect pairwise labeled data. We consider a challenging and practical problem called Early Active Learning, which is applied to the early stage of experiments when there is no pre-labeled sample available as references for human annotating. Previous early active learning methods suffer from two limitations for Re-ID. First, these instance-based algorithms select instances rather than pairs, which can result in missing optimal pairs for Re-ID. Second, most of these methods only consider the representativeness of instances, which can result in selecting less diverse and less informative pairs. To overcome these limitations, we propose a novel pair-based active learning for Re-ID. Our algorithm selects pairs instead of instances from the entire dataset for annotation. Besides representativeness, we further take into account the uncertainty and the diversity in terms of pairwise relations. Therefore, our algorithm can produce the most representative, informative, and diverse pairs for Re-ID data annotation. Extensive experimental results on five benchmark Re-ID datasets have demonstrated the superiority of the proposed pair-based early active learning algorithm.
- D. S. Cheng, M. Cristani, M. Stoppa, L. Bazzani, and V. Murino. 2011. Custom pictorial structures for re-identification. In Proceedings of the British Machine Vision Conference (BMVC).Google Scholar
- Frédéric Delbos and Jean Charles Gilbert. 2003. Global Linear Convergence of an Augmented Lagrangian Algorithm for Solving Convex Quadratic Optimization Problems. Ph.D. Dissertation. INRIA.Google Scholar
- Guodong Ding, Shanshan Zhang, Salman Khan, Zhenmin Tang, Jian Zhang, and Fatih Porikli. 2019. Feature affinity based pseudo labeling for semi-supervised person re-identification. IEEE Transactions on Multimedia 21, 11 (2019), 2891--2902.Google ScholarCross Ref
- Hehe Fan, Liang Zheng, Chenggang Yan, and Yi Yang. 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Transations on Multimedia Computing Communications and Applications 14, 4, Article 83 (Oct. 2018), 18 pages. DOI:https://doi.org/10.1145/3243316Google Scholar
- Xing Fan, Wei Jiang, Hao Luo, and Mengjuan Fei. 2019. Spherereid: Deep hypersphere manifold embedding for person re-identification. Journal of Visual Communication and Image Representation 60 (2019), 51--58.Google ScholarDigital Library
- Douglas Gray, Shane Brennan, and Hai Tao. 2007. Evaluating appearance models for recognition, reacquisition, and tracking. In Proceedings of the IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), Vol. 3.Google Scholar
- Martin Hirzer, Csaba Beleznai, Peter M. Roth, and Horst Bischof. 2011. Person re-identification by descriptive and discriminative classification. In Scandinavian Conference on Image Analysis. Springer, 91--102.Google ScholarCross Ref
- Sheng-Jun Huang, Rong Jin, and Zhi-Hua Zhou. 2010. Active learning by querying informative and representative examples. In Advances in Neural Information Processing Systems (NIPS). 892--900.Google Scholar
- Srikrishna Karanam, Mengran Gou, Ziyan Wu, Angels Rates-Borras, Octavia Camps, and Richard J. Radke. 2019. A systematic evaluation and benchmark for person re-identification: Features, metrics, and datasets. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 3 (2019), 523--536.Google ScholarDigital Library
- Srikrishna Karanam, Yang Li, and Richard J. Radke. 2015. Person re-identification with discriminatively trained viewpoint invariant dictionaries. In Proceedings of the IEEE International Conference on Computer Vision. 4516--4524.Google Scholar
- Elyor Kodirov, Tao Xiang, Zhenyong Fu, and Shaogang Gong. 2016. Person re-identification by unsupervised l 1 graph learning. In Proceedings of the European Conference on Computer Vision. Springer, 178--195.Google ScholarCross Ref
- David D. Lewis and Jason Catlett. 1994. Heterogeneous uncertainty sampling for supervised learning. In Machine Learning Proceedings 1994. Elsevier, 148--156.Google Scholar
- Zhihui Li, Lina Yao, Xiaojun Chang, Kun Zhan, Jiande Sun, and Huaxiang Zhang. 2019. Zero-shot event detection via event-adaptive concept relevance mining. Pattern Recognition 88 (2019), 595--603.Google ScholarDigital Library
- Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z. Li. 2015. Person re-identification by local maximal occurrence representation and metric learning. In CVPR. 2197--2206.Google Scholar
- Giuseppe Lisanti, Iacopo Masi, Andrew D. Bagdanov, and Alberto Del Bimbo. 2015. Person re-identification by iterative re-weighted sparse ranking. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 8 (2015), 1629--1642.Google ScholarDigital Library
- Giuseppe Lisanti, Iacopo Masi, and Alberto Del Bimbo. 2014. Matching people across camera views using kernel canonical correlation analysis. In Proceedings of the International Conference on Distributed Smart Cameras. ACM, 10.Google ScholarDigital Library
- Wenhe Liu, Xiaojun Chang, Ling Chen, and Yi Yang. 2017. Early active learning with pairwise constraint for person re-identification. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 103--118.Google ScholarCross Ref
- Wenhe Liu, Xiaojun Chang, Ling Chen, and Yi Yang. 2018. Semi-supervised Bayesian attribute learning for person re-identification. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence.Google Scholar
- Minnan Luo, Xiaojun Chang, Liqiang Nie, Yi Yang, Alexander G. Hauptmann, and Qinghua Zheng. 2018. An adaptive semisupervised feature analysis for video semantic recognition. IEEE Trans. Cybernetics 48, 2 (2018), 648--660.Google ScholarCross Ref
- Hieu T. Nguyen and Arnold Smeulders. 2004. Active learning using pre-clustering. In Proceedings of the 21st International Conference on Machine Learning. ACM.Google Scholar
- Feiping Nie, Hua Wang, Heng Huang, and Chris H. Q. Ding. 2013. Early active learning via robust representation and structured sparsity. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).Google Scholar
- Liqiang Nie, Xuemeng Song, and Tat-Seng Chua. 2016. Learning from multiple social networks. Synthesis Lectures on Information Concepts, Retrieval, and Services 8, 2 (2016), 1--118.Google ScholarCross Ref
- Liqiang Nie, Xiaochi Wei, Dongxiang Zhang, Xiang Wang, Zhipeng Gao, and Yi Yang. 2017. Data-driven answer selection in community QA systems. IEEE Transactions on Knowledge and Data Engineering 29, 6 (2017), 1186--1198.Google ScholarDigital Library
- Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, and Yonghong Tian. 2016. Unsupervised cross-dataset transfer learning for person re-identification. In CVPR. 1306--1315.Google Scholar
- Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, and Carlo Tomasi. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Conference on Computer Vision Workshop on Benchmarking Multi-Target Tracking.Google ScholarCross Ref
- H. Sebastian Seung, Manfred Opper, and Haim Sompolinsky. 1992. Query by committee. In Proceedings of the 5th Annual Workshop on Computational Learning Theory. ACM, 287--294.Google ScholarDigital Library
- Niall Twomey, Tom Diethe, and Peter Flach. 2015. Bayesian active learning with evidence-based instance selection. In Workshop on Learning over Multiple Contexts, European Conference on Machine Learning.Google Scholar
- Hanmo Wang, Xiaojun Chang, Lei Shi, Yi Yang, and Yi-Dong Shen. 2018. Uncertainty sampling for action recognition via maximizing expected average precision. In IJCAI. 964--970.Google Scholar
- Yu Wu, Yutian Lin, Xuanyi Dong, Yan Yan, Wanli Ouyang, and Yi Yang. 2018. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5177--5186.Google ScholarCross Ref
- Tong Xiao, Hongsheng Li, Wanli Ouyang, and Xiaogang Wang. 2016. Learning deep feature representations with domain guided dropout for person re-identification. In CVPR. 1249--1258.Google Scholar
- Eric P. Xing, Michael I. Jordan, Stuart J. Russell, and Andrew Y. Ng. 2003. Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems. 521--528.Google ScholarDigital Library
- Fei Xiong, Mengran Gou, Octavia Camps, and Mario Sznaier. 2014. Person re-identification using kernel-based metric learning methods. In Proceedings of the European Conference on Computer Vision. Springer, 1--16.Google ScholarCross Ref
- Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, and Stephen Lin. 2007. Graph embedding and extensions: A general framework for dimensionality reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 1 (2007).Google ScholarCross Ref
- Yi Yang, Zhigang Ma, Feiping Nie, Xiaojun Chang, and Alexander G. Hauptmann. 2015. Multi-class active learning by uncertainty sampling with diversity maximization. International Journal of Computer Vision 113, 2 (2015), 113--127.Google ScholarDigital Library
- Kai Yu, Jinbo Bi, and Volker Tresp. 2006. Active learning via transductive experimental design. In Proceedings of the 23rd International Conference on Machine Learning. ACM, 1081--1088.Google ScholarDigital Library
- Li Zhang, Tao Xiang, and Shaogang Gong. 2016. Learning a discriminative null space for person re-identification. In CVPR. 1239--1248.Google Scholar
- Liang Zheng, Yi Yang, and Alexander G. Hauptmann. 2016. Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016).Google Scholar
- Liang Zheng, Hengheng Zhang, Shaoyan Sun, Manmohan Chandraker, Yi Yang, and Qi Tian. 2017. Person re-identification in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1367--1376.Google ScholarCross Ref
- Miao Zheng, Jiajun Bu, Chun Chen, Can Wang, Lijun Zhang, Guang Qiu, and Deng Cai. 2011. Graph regularized sparse coding for image representation. IEEE Transactions on Image Processing 20, 5 (2011), 1327--1336.Google ScholarDigital Library
Index Terms
- Pair-based Uncertainty and Diversity Promoting Early Active Learning for Person Re-identification
Recommendations
Cluster and Scatter: A Multi-grained Active Semi-supervised Learning Framework for Scalable Person Re-identification
MM '21: Proceedings of the 29th ACM International Conference on MultimediaActive learning has recently attracted increasing attention in the task of person re-identification, due to its unique scalability that not only maximally reduces the annotation cost but also retains the satisfying performance. Although some preliminary ...
Combining active learning and semi-supervised for improving learning performance
ISABEL '11: Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication TechnologiesIn many learning tasks, there are abundant unlabeled samples but the number of labeled training samples is limited, because labeling the samples requires the efforts of human annotators and expertise. There are three major techniques for labeling the ...
Learning Multiple Kernel Metrics for Iterative Person Re-Identification
In person re-identification most metric learning methods learn from training data only once, and then they are deployed for testing. Although impressive performance has been achieved, the discriminative information from successfully identified test ...
Comments