Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
CVPR 2024(2023)
摘要
Human intelligence can retrieve any person according to both visual and
language descriptions. However, the current computer vision community studies
specific person re-identification (ReID) tasks in different scenarios
separately, which limits the applications in the real world. This paper strives
to resolve this problem by proposing a new instruct-ReID task that requires the
model to retrieve images according to the given image or language instructions.
Our instruct-ReID is a more general ReID setting, where existing 6 ReID tasks
can be viewed as special cases by designing different instructions. We propose
a large-scale OmniReID benchmark and an adaptive triplet loss as a baseline
method to facilitate research in this new setting. Experimental results show
that the proposed multi-purpose ReID model, trained on our OmniReID benchmark
without fine-tuning, can improve +0.5
CUHK03 for traditional ReID, +6.4
for clothes-changing ReID, +11.7
based clothes-changing ReID when using only RGB images, +24.9
real2 for our newly defined language-instructed ReID, +4.3
visible-infrared ReID, +2.6
datasets, the model, and code will be available at
https://github.com/hwz-zju/Instruct-ReID.
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