ASPD-Net: Self-aligned part mask for improving text-based person re-identification with adversarial representation learning. (November 2022)

• Record Type: Journal Article
• Authors: Wang, Zijie; Xue, Jingyi; Wan, Xili; Zhu, Aichun; Li, Yifeng; Zhu, Xiaomei; Hu, Fangqiang
• Is Part Of: Engineering applications of artificial intelligence. Volume 116(2022)
• Publication Date: 2022-11
• Subjects: Part mask detection -- Text-based person re-identification -- Adversarial learning; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105419
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Text-based person re-identification aims to retrieve images of the corresponding person from a large visual database according to a natural language description. When it comes to visual local information extraction, most of the state-of-the-art methods adopt either a strict uniform strategy which can be too rough to catch local details properly, or pre-processing with external cues which may suffer from the deviations of the pre-trained model and the large computation consumption. In this paper, we proposed an Adversarial Self-aligned Part Detecting Network (ASPD-Net) model which extracts and combines multi-granular visual and textual features. A novel Self-aligned Part Mask Module was presented to autonomously learn the information of human body parts, and obtain visual local features in a soft-attention manner by using K Self-aligned Part Mask Detectors. Regarding the main model branches as a generator, a discriminator is employed to determine whether the representation vector comes from the visual modality or the textual modality. With Adversarial Loss training, ASPD-Net can learn more robust representations, as long as it successfully tricks the discriminator. Experimental results demonstrate that the proposed ASPD-Net outperforms the previous methods and achieves the state-of-the-art performance on the CUHK-PEDES and RSTPReid datasets.