Saved in:
Bibliographic Details
Main Authors: Xiong, Ruoyan, Hou, Yuke, Torboh, Princess Retor, He, Hui, Zhang, Huanbin, Zhang, Yue, Wang, Yanpin, Guan, Huipan, Zhang, Shang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.14311
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912337296883712
author Xiong, Ruoyan
Hou, Yuke
Torboh, Princess Retor
He, Hui
Zhang, Huanbin
Zhang, Yue
Wang, Yanpin
Guan, Huipan
Zhang, Shang
author_facet Xiong, Ruoyan
Hou, Yuke
Torboh, Princess Retor
He, Hui
Zhang, Huanbin
Zhang, Yue
Wang, Yanpin
Guan, Huipan
Zhang, Shang
contents To address the challenge of capturing highly discriminative features in ther-mal infrared (TIR) tracking, we propose a novel Siamese tracker based on cross-channel fine-grained feature learning and progressive fusion. First, we introduce a cross-channel fine-grained feature learning network that employs masks and suppression coefficients to suppress dominant target features, en-abling the tracker to capture more detailed and subtle information. The net-work employs a channel rearrangement mechanism to enhance efficient in-formation flow, coupled with channel equalization to reduce parameter count. Additionally, we incorporate layer-by-layer combination units for ef-fective feature extraction and fusion, thereby minimizing parameter redun-dancy and computational complexity. The network further employs feature redirection and channel shuffling strategies to better integrate fine-grained details. Second, we propose a specialized cross-channel fine-grained loss function designed to guide feature groups toward distinct discriminative re-gions of the target, thus improving overall target representation. This loss function includes an inter-channel loss term that promotes orthogonality be-tween channels, maximizing feature diversity and facilitating finer detail capture. Extensive experiments demonstrate that our proposed tracker achieves the highest accuracy, scoring 0.81 on the VOT-TIR 2015 and 0.78 on the VOT-TIR 2017 benchmark, while also outperforming other methods across all evaluation metrics on the LSOTB-TIR and PTB-TIR benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking
Xiong, Ruoyan
Hou, Yuke
Torboh, Princess Retor
He, Hui
Zhang, Huanbin
Zhang, Yue
Wang, Yanpin
Guan, Huipan
Zhang, Shang
Computer Vision and Pattern Recognition
To address the challenge of capturing highly discriminative features in ther-mal infrared (TIR) tracking, we propose a novel Siamese tracker based on cross-channel fine-grained feature learning and progressive fusion. First, we introduce a cross-channel fine-grained feature learning network that employs masks and suppression coefficients to suppress dominant target features, en-abling the tracker to capture more detailed and subtle information. The net-work employs a channel rearrangement mechanism to enhance efficient in-formation flow, coupled with channel equalization to reduce parameter count. Additionally, we incorporate layer-by-layer combination units for ef-fective feature extraction and fusion, thereby minimizing parameter redun-dancy and computational complexity. The network further employs feature redirection and channel shuffling strategies to better integrate fine-grained details. Second, we propose a specialized cross-channel fine-grained loss function designed to guide feature groups toward distinct discriminative re-gions of the target, thus improving overall target representation. This loss function includes an inter-channel loss term that promotes orthogonality be-tween channels, maximizing feature diversity and facilitating finer detail capture. Extensive experiments demonstrate that our proposed tracker achieves the highest accuracy, scoring 0.81 on the VOT-TIR 2015 and 0.78 on the VOT-TIR 2017 benchmark, while also outperforming other methods across all evaluation metrics on the LSOTB-TIR and PTB-TIR benchmarks.
title DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.14311