Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
CoRR(2023)
摘要
Prevalent nighttime ReID methods typically combine relighting networks and
ReID networks in a sequential manner, which not only restricts the ReID
performance by the quality of relighting images, but also neglects the
effective collaborative modeling between image relighting and person ReID
tasks. To handle these problems, we propose a novel Collaborative Enhancement
Network called CENet, which performs the multilevel feature interactions in a
parallel framework, for nighttime person ReID. In particular, CENet is a
parallel Transformer network, in which the designed parallel structure can
avoid the impact of the quality of relighting images on ReID performance. To
perform effective collaborative modeling between image relighting and person
ReID tasks, we integrate the multilevel feature interactions in CENet.
Specifically, we share the Transformer encoder to build the low-level feature
interaction, and then perform the feature distillation to transfer the
high-level features from image relighting to ReID. In addition, the sizes of
existing real-world nighttime person ReID datasets are small, and large-scale
synthetic ones exhibit substantial domain gaps with real-world data. To
leverage both small-scale real-world and large-scale synthetic training data,
we develop a multi-domain learning algorithm, which alternately utilizes both
kinds of data to reduce the inter-domain difference in the training of CENet.
Extensive experiments on two real nighttime datasets, Night600 and
RGBNT201_rgb, and a synthetic nighttime ReID dataset are conducted
to validate the effectiveness of CENet. We will release the code and synthetic
dataset.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要