Manifold-based aggregation clustering for unsupervised vehicle re-identification

Most vehicle re-identification (V-reID) approaches are based on supervised learning methods which require a considerable amount of tedious and impractical annotations. In this paper, we propose a novel unsupervised V-reID approach based on Manifold-based Aggregation Clustering (MAC) with the unknown number of clusters. The proposed MAC is implemented by alternatively conducting two modules, i.e., deep feature learning module and aggregation clustering module. Specifically, deep feature learning module is responsible for training a convolutional neural network to encourage deep features to be close to the centroids of corresponding clusters which are yielded by an aggregation clustering mechanism based on manifold distance in the feature space. Moreover, the classification-agglomeration loss and manifold-based seeds searching criterion are proposed to improve the discriminative power of the learned features and deal with the problem of varied visual appearance respectively. Note that both annotations and even the certain number of vehicle identities are unknown for the proposed method, which is totally consistent with the real-world unsupervised V-reID condition. Extensive experiments on VehicleID and Veri-776 benchmark datasets show that the proposed method outperforms the state-of-the-art unsupervised V-reID approaches. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

The paper proposes a novel unsupervised vehicle re-identification approach based on Manifold-based Aggregation Clustering (MAC) with an unknown number of clusters. The approach outperforms state-of-the-art unsupervised V-reID methods on VehicleID and Veri-776 benchmark datasets.