UnbiasNet: Vehicle Re-Identification Oriented Unbiased Feature Enhancement by Using Causal Effect

• Published in: IEEE transactions on intelligent transportation systems Vol. 25; no. 2; pp. 1925 - 1937
• Main Authors: Huang, Junhao, Deng, Yuhui, Wang, Ke, Li, Zhangwei, Tang, Zhimin, Ding, Weiping
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Annotations; Benchmark testing; causal effect-based joint constraint; Computational modeling; computer vision; Feature extraction; Modules; Task analysis; Training; Unbiased feature orientation; vehicle re-identification
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2023.3317294

Vehicle re-identification is a crucial task that matches images of the same vehicle across different camera viewpoints. Many previous attention-based studies have approached this problem by exploring the regions of interest in vehicles. However, the generated attention in these models is susceptible to noisy data, as they are unable to provide powerful supervision to distinguish biased and unbiased clues during the attention learning process. To address the problems mentioned above, we aim to design a robust vehicle re-ID network that utilizes the causal effect to effectively transfer attention from biased to unbiased clues. In this paper, we propose an unbiased feature-enhanced network (UnbiasNet), which consists of an unbiased feature-aware block (UFAB) and a novel causal effect-based joint constraint (CEC). In particular, we propose an unbiased feature-aware block as an attention module to extract rich and discriminative information. We conduct a counterfactual intervention on our attention module to generate biased feature representations. Moreover, we propose a novel causal effect-based joint constraint that consists of original prediction constraint and total indirect effect constraint. The original prediction constraint ensures that unbiased feature-aware block converges correctly. The total indirect effect constraint utilizes the generated biased features as supervisory information to motivate unbiased feature-aware block to explore a greater number of unbiased features during the training process. Our approach had an inference time of 1.39 ms per image, which introduces only a few parameters during the training phase and none during the testing phase. We carry out comprehensive experiments to illustrate the effectiveness of the UnbiasNet on three challenging datasets.