Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking
This work addresses the challenge of designing efficient networks for thermal infrared pedestrian tracking, which is an incremental improvement over using existing architectures like AlexNet and ResNet.
The paper tackled the problem of manually designing network architectures for thermal infrared pedestrian tracking by automatically searching for an optimal lightweight architecture, resulting in a high-performance network that is both parameter- and computation-efficient.
Manually-designed network architectures for thermal infrared pedestrian tracking (TIR-PT) require substantial effort from human experts. AlexNet and ResNet are widely used as backbone networks in TIR-PT applications. However, these architectures were originally designed for image classification and object detection tasks, which are less complex than the challenges presented by TIR-PT. This paper makes an early attempt to search an optimal network architecture for TIR-PT automatically, employing single-bottom and dual-bottom cells as basic search units and incorporating eight operation candidates within the search space. To expedite the search process, a random channel selection strategy is employed prior to assessing operation candidates. Classification, batch hard triplet, and center loss are jointly used to retrain the searched architecture. The outcome is a high-performance network architecture that is both parameter- and computation-efficient. Extensive experiments proved the effectiveness of the automated method.