Beijing Key Laboratory of Traffic Data Analysisand Mining, School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China.
Sensors (Basel). 2023 May 28;23(11):5152. doi: 10.3390/s23115152.
In vehicle re-identification, identifying a specific vehicle from a large image dataset is challenging due to occlusion and complex backgrounds. Deep models struggle to identify vehicles accurately when critical details are occluded or the background is distracting. To mitigate the impact of these noisy factors, we propose Identity-guided Spatial Attention (ISA) to extract more beneficial details for vehicle re-identification. Our approach begins by visualizing the high activation regions of a strong baseline method and identifying noisy objects involved during training. ISA generates an attention map to mask most discriminative areas, without the need for manual annotation. Finally, the ISA map refines the embedding feature in an end-to-end manner to improve vehicle re-identification accuracy. Visualization experiments demonstrate ISA's ability to capture nearly all vehicle details, while results on three vehicle re-identification datasets show that our method outperforms state-of-the-art approaches.
在车辆再识别中，由于遮挡和复杂的背景，从大型图像数据集中识别特定车辆具有挑战性。当关键细节被遮挡或背景干扰时，深度模型很难准确识别车辆。为了减轻这些噪声因素的影响，我们提出了身份引导空间注意力（ISA）来提取更有益的车辆再识别细节。我们的方法首先可视化强基线方法的高激活区域，并识别训练过程中涉及的噪声对象。ISA 生成注意力图来屏蔽最具判别力的区域，而无需手动注释。最后，ISA 图以端到端的方式细化嵌入特征，以提高车辆再识别的准确性。可视化实验表明，ISA 能够捕获几乎所有车辆细节，而在三个车辆再识别数据集上的结果表明，我们的方法优于最先进的方法。
