Weakening the Influence of Clothing on Person Re-identification through Universal Clothing Attribute Learning

Yuming Yan, Huimin Yu

Abstract:

Most existing Re-ID studies focus on the short term cloth-consistent setting and thus dominate by the visual appearance of clothing. However,the same person would wear different clothes and different people would wear the same clothes in reality, which invalidates these methods. To tackle the challenge of clothes change, we propose a Universal Clothing Attribute Learning network (UCAL) which can effectively weaken the influence of clothing and extract identity-related features through universal clothing attribute learning. For further study of cloth-changing Re-ID, we construct a large-scale dataset called CSCC with the following unique features: (1) Severe: A large
number of people have cloth-changing over four seasons. (2) High definition: The resolution of the cameras ranges from 1920×1080 to 3840×2160,which ensures that the recorded people are clear.Furthermore, we provide two variants of CSCC considering different degrees of cloth-changing,namely moderate and severe, so that researchers can effectively evaluate their models from various aspects. Experiments on several cloth-changing datasets including our CSCC and short-term dataset Market-1501 prove the superiority of UCAL.