Scale-Aware Face Detection

By Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan, Xiaolin Hu. 2017

116 citations recorded by the source corpus.

Convolutional neural network (CNN) based face detectors are inefficient in handling faces of diverse scales. They rely on either fitting a large single model to faces across a large scale range or multi-scale testing. Both are computationally expensive. We propose Scale-aware Face Detection (SAFD) to handle scale explicitly using CNN, and achieve better performance with less computation cost. Prior to detection, an efficient CNN predicts the scale distribution histogram of the faces. Then the scale histogram guides the zoom-in and zoom-out of the image. Since the faces will be approximately in uniform scale after zoom, they can be detected accurately even with much smaller CNN. Actually, more than 99% of the faces in AFW can be covered with less than two zooms per image. Extensive experiments on FDDB, MALF and AFW show advantages of SAFD.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Dynamic Neural Networks: A Survey (2021, neutral): “Sa & Sp Image segmentation [34], [129], [146], [148], [150], [154], [156], [216], [217], [218], [219], [220], Image-to-image translation [221], Object detection [110], [111], [147], [148], [164], Semantic image synthesis [222], [223], [224], Computer Image denoising [225], Fine-grained classificatio”
Revisiting the Sibling Head in Object Detector (2020, background): “generic object classification task, the specialized sibling head for both classification and localization comes into focus and is widely used in most of advanced detectors including single stage family [25, 33, 12], two-stage family [5, 18, 40, 26, 19] and anchor free family [17].”
Object Detection in 20 Years: A Survey (2019, unknown): “Another recent improvement is to predict the scale distribution of objects in an image and then adaptively rescale the image according to it [181], [182].”
FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors (2017, methodology): “g images according to their face regions and resize to128without any pre-alignment operation. Example training images from celebA and Helen are shown in Fig. 6. For testing, any popular face detector [9] can be used to obtain the cropped 5 Figure 7:Ablation study on effects of estimated priors. ima”
Object Detection With Deep Learning: A Review (2018, methodology): “efficient CNN to predict the scale distribution histogram of the faces and took this histogram to guide the zoom-in and zoomout of the image [171].”
Recent Advances in Deep Learning for Object Detection (2019, methodology): “Unlike this method, Hao et al. [190] proposed a Scale Aware Face network which addresses scale issues without incurring signiﬁcant computation costs.”
RetinaFace: Single-stage Dense Face Localisation in the Wild (2019, background): “Even though the sliding-window on image pyramid was the leading detection paradigm [19, 32], with the emergence of feature pyramid [28], sliding-anchor [43] on multi-scale feature maps [68, 49], quickly dominated face detection.”