Improving unsupervised pedestrian re-identification with enhanced feature representation and robust clustering

Pedestrian re-identification (re-ID) is an important research direction in computer vision, with extensive applications in pattern recognition and monitoring systems. Due to uneven data distribution, and the need to solve clustering standards and similarity evaluation problems, the performance of unsupervised methods is limited. To address these issues, an improved unsupervised re-ID method, called Enhanced Feature Representation and Robust Clustering (EFRRC), which combines EFRRC is proposed. First, a relation network that considers the relations between each part of the pedestrian's body and other parts is introduced, thereby obtaining more discriminative feature representations. The network makes the feature at the single-part level also contain partial information of other body parts, making it more discriminative. A global contrastive pooling (GCP) module is introduced to obtain the global features of the image. Second, a dispersion-based clustering method, which can effectively evaluate the quality of clustering and discover potential patterns in the data is designed. This approach considers a wider context of sample-level pairwise relationships for robust cluster affinity assessment. It effectively addresses challenges posed by imbalanced data distributions in complex situations. The above structures are connected through a clustering contrastive learning framework, which not only improves the discriminative power of features and the accuracy of clustering, but also solves the problem of inconsistent clustering updates. Experimental results on three public datasets demonstrate the superiority of our method over existing unsupervised re-ID methods. The authors improve the robustness of multi-granularity features by means of relational networks and convolutional neural network-based dual branching structure. The introduction of a clustering method with discretisation measure solves the problem of inhomogeneous data distribution and cluster quality, and the application of clustering contrast learning improves the consistency of feature updating. image