S^3FD: Single Shot Scale-Invariant Face Detector

By Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, S. Li. IEEE International Conference on Computer Vision, 2017

685 citations recorded by the source corpus.

This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S3FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we try to solve the common problem that anchorbased detectors deteriorate dramatically as the objects become smaller. We make contributions in the following three aspects: 1) proposing a scale-equitable face detection framework to handle different scales of faces well. We tile anchors on a wide range of layers to ensure that all scales of faces have enough features for detection. Besides, we design anchor scales based on the effective receptive field and a proposed equal proportion interval principle; 2) improving the recall rate of small faces by a scale compensation anchor matching strategy; 3) reducing the false positive rate of small faces via a max-out background label. As a consequence, our method achieves state-of-theart detection performance on all the common face detection benchmarks, including the AFW, PASCAL face, FDDB and WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dcf71245addaf66a868221041aabe23c0a074312

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

VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency (2021, methodology): “To obtain the ROIs from the face track, we use an SFD face detector [15] to detect 68 facial landmarks.”
Attentional Feature Fusion (2020, background): “Numerous studies have emphasized this issue that arises when designing CNNs, i.e., that the receptive ﬁelds of predictors should match the object scale range [52, 34, 35, 22].”
Character Matters: Video Story Understanding with Character-Aware Relations (2020, positive): “We utilize a state-of-the-art face detector (Zhang et al. 2017) to localize faces in each frame and extract their 256-dimensional visual features f ∈ R 256 using LightCNN (Wu et al. 2018), considering its effectiveness at general face identiﬁcation, i.e., identifying different faces of the same…”
ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch (2018, background): “Recent researches on one-stage approach focus on enriching features for detection (Fu et al. 2017), designing different architecture (Zhang et al. 2018) and addressing class imbalance issue (Zhang et al. 2017; Lin et al. 2017b).”
Benchmarking Low-Light Image Enhancement and Beyond (2021, background): “…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 Reﬁnement Network (SRN) (Chi et al. 2018), and Faster…”
Is Someone Speaking?: Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection (2021, neutral): “We understand that both LRS3 and VoxCeleb2 use the S3FD face detection method [49] to provide ground truth face tracking of the speakers.”
Single-Shot Refinement Neural Network for Object Detection (2017, methodology): “To improve the accuracy, some one-stage methods [23, 27, 54] aim to address the extreme class imbalance problem by re-designing the loss function or classification strategies.”
Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark (2022, neutral): “The scale imbalance problem is another central issue hindering scale-invariant object detection (Zhang et al., 2017; Oksuz et al., 2021; Ming et al., 2019).”
Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “With the help of the devised scale compensation anchor matching strategy, S 3 FD [60] increases the matched anchors of tiny faces, thereby improving the recall rate.”
DeepPrivacy: A Generative Adversarial Network for Face Anonymization (2019, methodology): “For bounding box annotation, we use the Single Shot Scaleinvariant Face Detector [32].”
Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild (2020, methodology): “…the AP performance of our method against the some previous state-of-the-art face detectors (Yang et al. 2016; Zhang et al. 2016; Zhu et al. 2017b; Hu and Ramanan 2017; Najibi et al. 2017; Zhang et al. 2017b; Wang et al. 2017a,b; Zhu et al. 2018; Zhang et al. 2018a) on WIDER FACE validation set.”
Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis (2022, methodology): “The video frames are pre-processed using the S 3 FD face detector [69] to obtain face crops as done in Prajwal et al .”