Fine and Coarse-Grained Feature Learning for Unsupervised Person Re-identification

Most supervised learning methods are currently used to solve the task of person re-identification (Re-ID) and have yielded good results. But these methods still have disadvantages such as the need for manual annotation of training data. Especially for large data sets, they need too high cost of manual annotation and the data are difficult to obtain for fully pairwise labeling. So unsupervised learning becomes a necessarily trend for person Re-ID, and we decide to solve the task via unsupervised learning method. Moreover, global features focus on spatial integrity of person features, and local ones help to highlight discriminative features of different patches. Therefore, we propose a fine and coarse-grained unsupervised (FCU) learning framework of global and local branches' feature learning to solve Re-ID task. Specifically, for local branch, extract patches from a feature map which learned on a PatchNet network of images, and learn their fine-grained features to close similar patches and push away dissimilar ones. For global branch, maximize the diversity between classes by repelled loss and similarity within classes by attracted loss, then similarity and diversity in the unlabeled datasets are used as information for unsupervised cluster merging and learning their coarse-grained features. The two branches are used to jointly achieve the effect of increasing inter-class differences and intra-class similarity. A large number of experiments verify the superiority of our method for unsupervised person re-identification.