Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification
This work is significant for smart city applications requiring large-scale intelligent monitoring, specifically by reducing the annotation burden for vehicle re-identification.
This paper addresses unsupervised vehicle re-identification, a task challenged by significant appearance variations across different viewpoints. The authors propose a viewpoint-aware progressive clustering algorithm that first divides the feature space by predicted viewpoints and then performs progressive clustering. The method demonstrates promising performance on VeRi and VeRi-Wild datasets, both with and without domain adaptation.
Vehicle re-identification (Re-ID) is an active task due to its importance in large-scale intelligent monitoring in smart cities. Despite the rapid progress in recent years, most existing methods handle vehicle Re-ID task in a supervised manner, which is both time and labor-consuming and limits their application to real-life scenarios. Recently, unsupervised person Re-ID methods achieve impressive performance by exploring domain adaption or clustering-based techniques. However, one cannot directly generalize these methods to vehicle Re-ID since vehicle images present huge appearance variations in different viewpoints. To handle this problem, we propose a novel viewpoint-aware clustering algorithm for unsupervised vehicle Re-ID. In particular, we first divide the entire feature space into different subspaces according to the predicted viewpoints and then perform a progressive clustering to mine the accurate relationship among samples. Comprehensive experiments against the state-of-the-art methods on two multi-viewpoint benchmark datasets VeRi and VeRi-Wild validate the promising performance of the proposed method in both with and without domain adaption scenarios while handling unsupervised vehicle Re-ID.