首页|Researcher from Northeastern University Reports Details of New Studies and Findings in the Area of Artificial Intelligence (Doubly stochastic subdomain mining with sample reweighting for unsupervised domain adaptive person re-identification)
Researcher from Northeastern University Reports Details of New Studies and Findings in the Area of Artificial Intelligence (Doubly stochastic subdomain mining with sample reweighting for unsupervised domain adaptive person re-identification)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Investigators publish new report on artificial intelligence. According to news reporting out of Shenyang, People’s Republic of China, by NewsRx editors, research stated, “Clustering-based unsupervised domain adaptive person re-identification methods have achieved remarkable progress.” Our news correspondents obtained a quote from the research from Northeastern University: “However, existing works are easy to fall into local minimum traps due to the optimization of two variables, feature representation and pseudo labels. Besides, the model can also be hurt by the inevitable false assignment of pseudo labels. In order to solve these problems, we propose the Doubly Stochastic Subdomain Mining (DSSM) to prevent the nonconvex optimization from falling into local minima in this paper. And we also design a novel reweighting algorithm based on the similarity correlation coefficient between samples which is referred to as Maximal Heterogeneous Similarity (MHS), it can reduce the adverse effect caused by noisy labels.”
Northeastern UniversityShenyangPeople’s Republic of ChinaAsiaArtificial Intelligence
NETL
NSTL
