.png){kind=icon}
返回
Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features
.png){kind=icon}
PRE
AI
DOI：10.1145/3626825.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To reduce computational redundancies, a common approach is to integrate detection and re-identification (Re-ID) into a single network in multi-object tracking (MOT), referred to as tracking by detection. Most of the previous research has focused on resolving the conflict between the detection and Re-ID branches, considering it a simple coupling. In our work, we uncover that the entangled state between the detection and Re-ID tasks is much more complex than previous idea, resulting in a form of competition that degrades performance. To address the preceding issue, we propose a feature disentanglement network that deeply disentangles the intricately interwoven latent space of features and provides differentiated feature maps for each individual task. Furthermore, considering the demand for shallow semantic features in the feature re-ID branch, we also introduce a feature re-globalization module to enrich the shallow semantics. By integrating two distinct networks into a one-shot online MOT method, we develop a robust MOT tracker (named HDGTrack). We conduct extensive experiments on a number of benchmarks, and our experimental results demonstrate that our method significantly outperforms state-of-the-art MOT methods. Besides, HDGTrack is efficient and can run at 13.9 (MOT17) and 8.7 (MOT20) frames per second.
Keyword:
Multiple object tracking
Feature disentanglement network
one-shot tracking
feature enhancement
期刊
IF:
6
论文数:
2.0K
被引数:
5.4K
机构
引用论文
.png){kind=icon}
分享收藏The impact of temperature dependency of the building insulation thermal conductivity in the Canadian climate加拿大气候对建筑保温导热系数温度依赖性的影响
OAAI
OAAI分享收藏Generation of hydroxyl radicals by urban suspended particulate air matter. The role of iron ions城市悬浮颗粒物产生羟基自由基。铁离子的作用:
PREAI
分享收藏
查看更多内容