Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns

Lv, Jianming; Chen, Weihang; Li, Qing; Yang, Chunlin

doi:10.48550/arxiv.1803.07293

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Qian et al [24] proposed a pose-normalized image generator to generate different pose images for the same person. Peng et al [20] propose an asymmetric multi-task dictionary learning method to transfer the view-invariant representation learned from source data to target data.…”

Section: A Person Reid Under Intensive Appearance Variationsmentioning

confidence: 99%

Apparel-invariant Feature Learning for Apparel-changed Person Re-identification

Yu¹,

Zhao²,

Hong³

et al. 2020

Preprint

View full text Add to dashboard Cite

With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which persons' appearance rarely changes. In real-world applications such as in a shopping mall, the same person's clothing may change, and different persons may wearing similar clothes. All these cases can result in an inconsistent ReID performance, revealing a critical problem that current ReID models heavily rely on person's apparels. Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes. In this work, we tackle this problem from the viewpoint of invariant feature representation learning. The main contributions of this work are as follows.(1) We propose the semi-supervised Apparel-invariant Feature Learning (AIFL) framework to learn an apparel-invariant pedestrian representation using images of the same person wearing different clothes. ( 2) To obtain images of the same person wearing different clothes, we propose an unsupervised apparelsimulation GAN (AS-GAN) to synthesize cloth changing images according to the target cloth embedding. It's worth noting that the images used in ReID tasks were cropped from real-world lowquality CCTV videos, making it more challenging to synthesize cloth changing images. We conduct extensive experiments on several datasets comparing with several baselines. Experimental results demonstrate that our proposal can improve the ReID performance of the baseline models.

show abstract

Section: A Person Reid Under Intensive Appearance Variationsmentioning

confidence: 99%