PyramidBox: A Context-assisted Single Shot Face Detector

By Xu Tang, Daniel K. Du, Zeqiang He, Jingtuo Liu. European Conference on Computer Vision, 2018

409 citations recorded by the source corpus.

Face detection has been well studied for many years and one of remaining challenges is to detect small, blurred and partially occluded faces in uncontrolled environment. This paper proposes a novel context-assisted single shot face detector, named \emph{PyramidBox} to handle the hard face detection problem. Observing the importance of the context, we improve the utilization of contextual information in the following three aspects. First, we design a novel context anchor to supervise high-level contextual feature learning by a semi-supervised method, which we call it PyramidAnchors. Second, we propose the Low-level Feature Pyramid Network to combine adequate high-level context semantic feature and Low-level facial feature together, which also allows the PyramidBox to predict faces of all scales in a single shot. Third, we introduce a context-sensitive structure to increase the capacity of prediction network to improve the final accuracy of output. In addition, we use the method of Data-anchor-sampling to augment the training samples across different scales, which increases the diversity of training data for smaller faces. By exploiting the value of context, PyramidBox achieves superior performance among the state-of-the-art over the two common face detection benchmarks, FDDB and WIDER FACE. Our code is available in PaddlePaddle: \href{this https URL}{\url{this https URL}}.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/58bf72750a8f5100e0c01e55fd1b959b31e7dbce

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

DSFD: Dual Shot Face Detector (2018, methodology): “Some works [27, 39] analyze a series of reasonable anchor scales and anchor compensation strategy to increase positive anchors.”
Recent Advances in Deep Learning for Object Detection (2019, background): “[185] proposed a state-of-the-art context assisted single shot face detector, named PyramidBox to handle the hard face detection problem.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, positive): “1) Baseline Composition: We test four state-of-the-art deep face detectors: (1) Dual Shot Face Detector ( DSFD ) [147] 10 ; (2) Pyramidbox [148] 11 ; (3) Single Stage Headless Face Detector ( SSH ) [149] 12 ; (4) Faster RCNN [150].”
Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild (2020, methodology): “(Tang et al. 2018) introduces an context-assisted anchor-based method to utilize supervised information on learning contextual features for detecting small, blurred and partially occluded faces in the unconstrained conditions.”
YOLO-FaceV2: A Scale and Occlusion Aware Face Detector (2022, methodology): “Pyra-midBox [44] designs a context-sensitive predict module in which they replace the convolution layers of context module in SSH by the residual prediction module of DSSD. RetinaFace [45] applies independent context modules on ﬁve feature pyramid levels to increase the receptive ﬁeld and enhance…”
Detecting small faces in the wild based on generative adversarial network and contextual information (2019, methodology): “Actually, the context plays a signiﬁcant role in some computer vision tasks [13] , like tracking, pedestrian detection, object detection, etc.”
Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “PyramidBox [125] makes full use of contextual cues to ﬁnd small and blur faces that are indistinguishable from background.”
RetinaFace: Single-stage Dense Face Localisation in the Wild (2019, methodology): “SSD [30, 68] and Reti-naNet [29, 49]).”
Benchmarking Low-Light Image Enhancement and Beyond (2021, methodology): “For the task-driven metrics, we adopt the face detection results of Dual Shot Face Detec-torf (DSFD) (Li et al. 2019), PyramidBox (Tang et al. 2018), Single Shot Scale-Invariant Face Detector (S 3 FD) (Zhang et al. 2017), Single Stage Headless Face Detector (SSH) (Najibi et al. 2017), Selective Reﬁn”