.png){kind=icon}
返回
A Reliable Sample Selection Strategy for Weakly Supervised Visual Tracking
.png){kind=icon}
PRE
AI
DOI：10.1109/TR.2022.3162346.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reliability is an important property in the applied engineering systems, especially in visual tracking. The supervised visual tracking method uses reliable ground truth that is manually annotated, which is hard to get in many applications. However, weakly supervised visual trackings are limited by the low-quality labels. Therefore, a reliable sample selection strategy is the most important issue for the weakly supervised visual trackings. In this article, we propose an optimal sample selection strategy and apply it to the visual tracking system. The strategy first assesses the reliability of the samples according to the score map, where the score map is the pseudolabel generated by the upstream task to meet the needs of the downstream task. Then, the unreliable pseudolabels are replaced by reliable ground truth or discarded to overcome the degraded modeling problem by filtering low-quality samples. Finally, through comparison with multiple selection strategies, it is verified that the model trained using this strategy has the best performance. The proposed visual tracking model achieves the best performance among multiple assessment metrics in multiple datasets. Experiments verify that the scientific sample quality assessment method is very important. It can guide the improvement of model performance, which is of great help to the weakly supervised learning systems based on data.
Keyword:
Reliability
Feature extraction
Visualization
Target tracking
Task analysis
Training
Adaptation models
Label quality
sample selection
system reliability
visual tracking
weak supervision
期刊
IF:
5.7
论文数:
2.8K
被引数:
8.5K
机构
引用论文
Sustaining the efficiency of the Fe(0)/H2O system for Cr(VI) removal by MnO2 amendment.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Cobalt oxides nanoparticles supported on nitrogen-doped carbon nanotubes as high-efficiency cathode catalysts for microbial fuel cells负载在氮掺杂碳纳米管上的钴氧化物纳米颗粒作为微生物燃料电池的高效阴极催化剂
OAAI
OAAI分享收藏RFID-Pose: Vision-Aided Three-Dimensional Human Pose Estimation With Radio-Frequency IdentificationRfid-pose: 视觉辅助的三维人体姿态估计与射频识别
PREAI
分享收藏
查看更多内容