arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.00596cs.CVcs.LGeess.IV
收藏

基于特征金字塔和地标的Face检测

Face Detection with Feature Pyramids and Landmarks

Sertis Vision Lab(Sertis视觉实验室)

Samuel W. F. Earp, Pavit Noinongyao, Justin A. Cairns, Ankush Ganguly

摘要:

准确的人脸检测和人脸标志点定位是人脸识别系统的关键。我们提出了一系列三个单阶段RCNN,具有不同大小的骨干(MobileNetV 2 -25,MobileNetV 2 -100和ResNet 101)和一个专门在WIDER FACE数据集上训练的六层特征金字塔。我们比较了人脸检测和地标的准确性,使用八个上下文模块架构,四个由以前的研究和四个修改后的版本。我们没有发现任何证据表明,所提出的架构显着优于和假设,随机初始化的额外的层至少是同等重要的。为了证明这一点,我们提出了一个模型,该模型在WIDER FACE上实现了接近最先进的性能,并且还提供了具有简单上下文模块的高精度地标。我们还介绍了使用MobileNetV 2主干的结果,该主干在WIDER FACE硬验证集上实现了超过90%的平均精度,同时能够实时运行。通过与其他作者的比较,我们表明,我们的模型超过了类似大小的RCNN的最新技术水平,并与更重的网络的性能相匹配。

英文摘要:

Accurate face detection and facial landmark localization are crucial to any face recognition system. We present a series of three single-stage RCNNs with different sized backbones (MobileNetV2-25, MobileNetV2-100, and ResNet101) and a six-layer feature pyramid trained exclusively on the WIDER FACE dataset. We compare the face detection and landmark accuracies using eight context module architectures, four proposed by previous research and four modified versions. We find no evidence that any of the proposed architectures significantly overperform and postulate that the random initialization of the additional layers is at least of equal importance. To show this we present a model that achieves near state-of-the-art performance on WIDER FACE and also provides high accuracy landmarks with a simple context module. We also present results using MobileNetV2 backbones, which achieve over 90% average precision on the WIDER FACE hard validation set while being able to run in real-time. By comparing to other authors, we show that our models exceed the state-of-the-art for similar-sized RCNNs and match the performance of much heavier networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑