@article{Lin_Dong_Zheng_Yan_Yang_2019, title={A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/4898}, DOI={10.1609/aaai.v33i01.33018738}, abstractNote={<p>Most person re-identification (re-ID) approaches are based on supervised learning, which requires intensive manual annotation for training data. However, it is not only resourceintensive to acquire identity annotation but also impractical to label the large-scale real-world data. To relieve this problem, we propose a bottom-up clustering (BUC) approach to jointly optimize a convolutional neural network (CNN) and the relationship among the individual samples. Our algorithm considers two fundamental facts in the re-ID task, <em>i.e.</em>, <em>diversity</em> across different identities and <em>similarity</em> within the same identity. Specifically, our algorithm starts with regarding individual sample as a different identity, which maximizes the diversity over each identity. Then it gradually groups similar samples into one identity, which increases the similarity within each identity. We utilizes a diversity regularization term in the bottom-up clustering procedure to balance the data volume of each cluster. Finally, the model achieves an effective trade-off between the <em>diversity</em> and <em>similarity</em>. We conduct extensive experiments on the large-scale image and video re-ID datasets, including Market-1501, DukeMTMCreID, MARS and DukeMTMC-VideoReID. The experimental results demonstrate that our algorithm is not only superior to state-of-the-art unsupervised re-ID approaches, but also performs favorably than competing transfer learning and semi-supervised learning methods.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Lin, Yutian and Dong, Xuanyi and Zheng, Liang and Yan, Yan and Yang, Yi}, year={2019}, month={Jul.}, pages={8738-8745} }