.png){kind=icon}
Return
DLUT: Decoupled Learning-Based Unsupervised Tracker
.png){kind=icon}
OA
AI
DOI：10.3390/s24010083.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Unsupervised learning has shown immense potential in object tracking, where accurate classification and regression are crucial;
unsupervised trackers. However, the classification and regression branches of most unsupervised trackers calculate object similarities by sharing cross-correlation modules. This leads to high coupling between different branches, thus hindering the network per;
mance. To address the above issue, we propose a Decoupled Learning-based Unsupervised Tracker (DLUT). Specifically, we separate the training pipelines of different branches to unlock their inherent learning potential so that different branches can fully explore the focused feature regions of interest. Furthermore, we design independent adaptive decoupling-correlation modules according to the characteristics of each branch to obtain more discriminative and easily locatable feature response maps. Finally, to suppress the noise interference brought by unsupervised pseudo-label training and highlight the;
eground object, we propose a novel suppression-ranking-based unsupervised training strategy. Extensive experiments demonstrate that our DLUT outper;
ms state-of-the-art unsupervised trackers.
Keywords:
deep learning
object tracking
unsupervised learning
decoupled learning
pseudo-labels
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.5
Papers:
7.2W
Citations:
20.9W
Organization
Cited Papers
Ultrasound evaluation of hand, wrist and foot joint synovitis in systemic lupus erythematosus.png)
RheumatologyOAAI
RheumatologyIF0
OAAIShareSaveShareSaveShareSave
View more