Cross-Domain Pedestrian Attribute Recognition: Evaluation Criteria, a New Baseline and Remote Sensor-Based Application

The task of pedestrian attribute recognition (PAR) identifies a set of predefined attributes in pedestrian images from surveillance videos or collected imagery, which are often adopted as important mid-level features in higher-level tasks, such as person re-identification, pedestrian detection, etc. In these cases, the domain differences between datasets of different tasks will lead to clear performance degradation of the mainstream PAR methods. This degradation becomes significant in the application of remote sensor-based PAR, since the model is trained on traditional fixed-camera visual data while applied on UAV-based remote sensor data, facing more cross-domain challenges. To address these issues, we formally introduce in this paper the task of cross-domain pedestrian attribute recognition (CDPAR) for the first time, and efficiently establish a set of evaluation criteria for this new task. In addition, to facilitate the future research of CDPAR, we propose a new baseline method named local domain discriminator-based cross-domain pedestrian attribute recognition (LDCDPAR), by introducing a local domain discriminator based on adversarial training to effectively obtain the fine-grained domain-invariant features. Extensive well designed cross-domain experimental evaluation and application on remote sensor-based PAR demonstrate the value of the new CDPAR task, and validate the effectiveness of our new baseline method.