Selective Reﬁnement Network for High Performance Face Detection

doi:doi:10.57702/m99y7ppp

Selective Reﬁnement Network for High Performance Face Detection

High performance face detection remains a very challenging problem, especially when there exists many tiny faces. This paper presents a novel single-shot face detector, named Selective Reﬁnement Network (SRN), which introduces novel two-step classiﬁcation and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously.

BibTex:

@dataset{Cheng_Chi_and_Shifeng_Zhang_and_Junliang_Xing_and_Zhen_Lei_and_Stan_Z_Li_and_Xudong_Zou_2024,
    abstract = {High performance face detection remains a very challenging problem, especially when there exists many tiny faces. This paper presents a novel single-shot face detector, named Selective Reﬁnement Network (SRN), which introduces novel two-step classiﬁcation and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously.},
    author = {Cheng Chi and Shifeng Zhang and Junliang Xing and Zhen Lei and Stan Z. Li and Xudong Zou},
    doi = {10.57702/m99y7ppp},
    institution = {No Organization},
    keyword = {'face detection', 'single-shot face detector', 'two-step classiﬁcation', 'two-step regression'},
    month = {dec},
    publisher = {TIB},
    title = {Selective Reﬁnement Network for High Performance Face Detection},
    url = {https://service.tib.eu/ldmservice/dataset/selective-re-nement-network-for-high-performance-face-detection},
    year = {2024}
}