paper-with-me

홈 › Papers

Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking

2025-03-01 · Jiawen Zhu, Huayi Tang, Xin Chen, Xinying Wang, Dong Wang, Huchuan Lu

Efficient tracking has garnered attention for its ability to operate on resource-constrained platforms for real-world deployment beyond desktop GPUs. Current efficient trackers mainly follow precision-oriented trackers, adopting a one-stream framework with lightweight modules. However, blindly adhering to the one-stream paradigm may not be optimal, as incorporating template computation in every frame leads to redundancy, and pervasive semantic interaction between template and search region places stress on edge devices. In this work, we propose a novel asymmetric Siamese tracker named \textbf{AsymTrack} for efficient tracking. AsymTrack disentangles template and search streams into separate branches, with template computing only once during initialization to generate modulation signals. Building on this architecture, we devise an efficient template modulation mechanism to unidirectional inject crucial cues into the search features, and design an object perception enhancement module that integrates abstract semantics and local details to overcome the limited representation in lightweight tracker. Extensive experiments demonstrate that AsymTrack offers superior speed-precision trade-offs across different platforms compared to the current state-of-the-arts. For instance, AsymTrack-T achieves 60.8\% AUC on LaSOT and 224/81/84 FPS on GPU/CPU/AGX, surpassing HiT-Tiny by 6.0\% AUC with higher speeds. The code is available at https://github.com/jiawen-zhu/AsymTrack.

📄 PDF Abstract BibTeX arXiv:2503.00516

Code (1)

jiawen-zhu/asymtrack 공식 구현 pytorch

Tasks

CPUGPUVisual Tracking

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

On the Importance of Asymmetry for Siamese Representation Learning

2022-04-01 · CVPR 2022 1 · Xiao Wang, Haoqi Fan, Yuandong Tian, Daisuke Kihara 외

Many recent self-supervised frameworks for visual representation learning are based on certain forms of Siamese networks. Such networks are conceptually symmetric with two parallel encoders, but often practically asymmet…

Representation Learning

Adaptive Feature Discrimination and Denoising for Asymmetric Text Matching

2022-10-01 · COLING 2022 10 · Yan Li, Chenliang Li, Junjun Guo

Asymmetric text matching has becoming increasingly indispensable for many downstream tasks (e.g., IR and NLP). Here, asymmetry means that the documents involved for matching hold different amounts of information, e.g., a…

DenoisingText Matching

A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras

2019-02-04 · Icaro O. de Oliveira, Keiko V. O. Fonseca, Rodrigo Minetto

We describe in this paper a Two-Stream Siamese Neural Network for vehicle re-identification. The proposed network is fed simultaneously with small coarse patches of the vehicle shape's, with 96 x 96 pixels, in one stream…

Vehicle Re-Identification

A Two Stream Siamese Convolutional Neural Network for Person Re-Identification

2017-10-01 · ICCV 2017 10 · Dahjung Chung, Khalid Tahboub, Edward J. Delp

Person re-identification is an important task in video surveillance systems. It can be formally defined as establishing the correspondence between images of a person taken from different cameras at different times. In th…

Person Re-IdentificationVocal Bursts Valence Prediction

Learning to Fuse Asymmetric Feature Maps in Siamese Trackers

2020-12-04 · CVPR 2021 1 · Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao 외

Recently, Siamese-based trackers have achieved promising performance in visual tracking. Most recent Siamese-based trackers typically employ a depth-wise cross-correlation (DW-XCorr) to obtain multi-channel correlation i…

Video Object TrackingVisual Object TrackingVisual Tracking