.png){kind=icon}
返回
Lightweight full-convolutional siamese tracker
.png){kind=icon}
OA
AI
DOI：10.1016/j.knosys.2024.111439.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Although single object trackers have achieved advanced performance, their large-scale models hinder their application on limited resources platforms. Moreover, existing lightweight trackers only achieve a balance between 2 and 3 points in terms of parameters, performance, Flops and FPS. To achieve the optimal balance among these points, this paper proposes a lightweight full-convolutional Siamese tracker called LightFC. LightFC employs a novel efficient cross-correlation module (ECM) and a novel efficient rep-center head (ERH) to improve the feature representation of the convolutional tracking pipeline. The ECM uses an attention-like module design, which conducts spatial and channel linear fusion of fused features and enhances the nonlinearity of the fused features. Additionally, it refers to successful factors of current lightweight trackers and introduces skipconnections and reuse of search area features. The ERH reparameterizes the feature dimensional stage in the standard center-head and introduces channel attention to optimize the bottleneck of key feature flows. Comprehensive experiments show that LightFC achieves the optimal balance between performance, parameters, Flops and FPS. The precision score of LightFC outperforms MixFormerV2-S on LaSOT and TNL2K by 3.7% and 6.5%, respectively, while using 5x fewer parameters and 4.6x fewer Flops. Besides, LightFC runs 2x faster than MixFormerV2-S on CPUs. In addition, a higher-performance version named LightFC-vit is proposed by replacing a more powerful backbone network. The code and raw results can be found at https://github.com/LiYunfengLY F/LightFC.
Keyword:
Single object tracking
Lightweight network
Siamese Network
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏
SiamOAN: Siamese object-aware network for real-time target trackingSiamOAN: 用于实时目标跟踪的暹罗对象感知网络.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Comprehensive Underwater Object Tracking Benchmark Dataset and Underwater Image Enhancement With GANOAAI
OAAI分享收藏Viscoelastic testing in benign hematologic disorders: Clinical perspectives and future implications of point‐of‐care testing to assess hemostatic competenceTransfusionOAAI
TransfusionIF0
OAAI分享收藏 没有更多内容
没有更多内容