Embedding Adversarial Learning for Vehicle Re-Identification

• Published in: IEEE transactions on image processing Vol. 28; no. 8; pp. 3794 - 3807
• Main Authors: Lou, Yihang, Bai, Yan, Liu, Jun, Wang, Shiqi, Duan, Ling-Yu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; cross-view; Embedding; embedding adversarial learning; Gallium nitride; generative adversarial network; Generative adversarial networks; hard negatives; Image generation; Licenses; Machine learning; Optimization; Space vehicles; Task analysis; Training; Vehicle Re-Identification; Vehicles

The high similarities of different real-world vehicles and great diversities of the acquisition views pose grand challenges to vehicle re-identification (ReID), which traditionally maps the vehicle images into a high-dimensional embedding space for distance optimization, vehicle discrimination, and...