Saved in:
Bibliographic Details
Main Authors: Tang, Wen-Jia, Liu, Xiao, Gao, Peng, Wang, Fei, Yuan, Ru-Yue
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.16570
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916415172247552
author Tang, Wen-Jia
Liu, Xiao
Gao, Peng
Wang, Fei
Yuan, Ru-Yue
author_facet Tang, Wen-Jia
Liu, Xiao
Gao, Peng
Wang, Fei
Yuan, Ru-Yue
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16570
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking
Tang, Wen-Jia
Liu, Xiao
Gao, Peng
Wang, Fei
Yuan, Ru-Yue
Computer Vision and Pattern Recognition
Machine Learning
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.
title Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2402.16570