AE-Net: Appearance-Enriched Neural Network With Foreground Enhancement for Person Re-Identification

• Published in: IEEE transactions on emerging topics in computational intelligence pp. 1 - 15
• Main Authors: Zhu, Shangdong, Zhang, Yunzhou, Liu, Yixiu, Feng, Yu, Coleman, Sonya, Kerr, Dermot
• Format: Journal Article
• Language: English
• Published: IEEE 11.03.2025
• Subjects: Appearance-enriched neural network; Attention mechanisms; Body regions; Cameras; channel-grouped convolution and squeeze weighted module; Clutter; Convolution; Feature extraction; foreground-enhanced and background-suppressed module; Image resolution; Neural networks; person re-identification; Training; Visualization
• ISSN: 2471-285X; 2471-285X
• DOI: 10.1109/TETCI.2025.3543775

Person re-identification (Re-ID) in environments subject to intensive appearance and background variations due to seasons, weather conditions, illumination and human factors is a challenging task. A wide variety of existing algorithms address this problem either for appearance changes or background clutter, but neglect to explore a powerful framework to consider solving both cases simultaneously. To overcome this limitation, this research introduces an effective appearance-enriched neural network (AE-Net) with foreground enhancement based on generative adversarial nets (GANs) and an attention mechanism to enrich the appearance of person images while suppressing the influence of the background. Specifically, a channel-grouped convolution and squeeze weighted (CGCSW) module is first proposed to extract the powerful feature representation of individuals. Secondly, a foreground-enhanced and background-suppressed (FEBS) module is proposed to enhance the foreground of individual samples while weakening the impact of the background. Thirdly, A stage-wise consistency loss is presented to enable our model maintain consistent foreground-enhanced and background-suppressed stages. Finally, this study evaluates the proposed method and compares it with state-of-the-art approaches on three public datasets. The experimental results demonstrate the effectiveness and improvements achieved by using the presented architecture.