• Corpus ID: 234357892

Sample and Computation Redistribution for Efficient Face Detection

@article{Guo2021SampleAC,
  title={Sample and Computation Redistribution for Efficient Face Detection},
  author={Jia Guo and Jiankang Deng and Alexandros Lattas and Stefanos Zafeiriou},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.04714}
}
Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge. In this paper, we point out that training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. Motivated by these observations, we introduce two simple but effective methods (1) Sample Redistribution (SR), which augments training samples for the most needed… 

An Efficient Anchor-Free Face Detector with Attention Mechanisms

An efficient anchor-free face detector that focuses on a low flops regime and combines recent advances in generic object detection with the methods for detecting tiny faces is designed.

Image Grid Recognition and Regression for Fast and Accurate Face Detection

This paper proposes an effective anchor generation and bounding-box regression method that can make a good balance between speed and accuracy, and also work well in bad conditions and can effectively detect multi-scale faces.

MogFace: Towards a Deeper Appreciation on Face Detection

In this paper, three key components, Adaptive Online Incremental Anchor Mining Strategy, Selective Scale Enhancement Strategy and Hierarchical Context-Aware Module are separately proposed to boost the performance of face detectors.

YOLO5Face: Why Reinventing a Face Detector

A face detector based on YOLOv5 object detector is implemented and called YolO5Face, which can achieve state-of-the-art performance in almost all the Easy, Medium, and Hard subsets, exceeding the more complex designated face detectors.

Depth and Thermal Images in Face Detection - A Detailed Comparison Between Image Modalities

Results show that non-RGB solutions can be applied in practice with highly robust accuracy and their efficiency is close to RGB detectors, however, their performance depends on the environment and that circumstances are described later in this article.

Unsupervised and Semi-supervised Bias Benchmarking in Face Recognition

Experiments show that SPE-FR can accurately assess performance on data with no identity labels, and confidently reveal demographic biases in system performance.

Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression

A straightforward algorithm is implemented, in which joint face 3D mesh and 2D landmark regression are proposed for perspective 3D face reconstruction and 6DoF pose estimation.

Physically-Based Face Rendering for NIR-VIS Face Recognition

A novel method for paired NIR-VIS facial image generation and an IDentity-based Maximum Mean Discrepancy (ID-MMD) loss, which not only reduces the modality gap between NIR and VIS images at the domain level but encourages the network to focus on the identity features instead of facial details, such as poses and accessories.

3DMM-RF: Convolutional Radiance Fields for 3D Face Modeling

This work presents a facial 3D Morphable Model, which can accurately model a subject’s identity, pose and expression and render it in arbitrary illumination, and introduces a style-based generative network that synthesizes in one pass all and only the required rendering samples of a neural radiance.

Learning Audio-Visual embedding for Person Verification in the Wild

This work introduced weight-enhanced attentive statistics pooling for the first time in face verification and found that a strong correlation exists between modalities during pooling, so joint attentive pooling is proposed which contains cycle consistency to learn the implicit inter-frame weight.

References

SHOWING 1-10 OF 43 REFERENCES

ASFD: Automatic and Scalable Face Detector

This work proposes to search an effective FAE architecture, termed AutoFAE by a differentiable architecture search, which outperforms all existing FAE modules in face detection with a considerable margin, and builds a supernet, which automatically obtains a family of detectors under the different complexity constraints.

FaceBoxes: A CPU real-time face detector with high accuracy

This work proposes a novel face detector, named FaceBoxes, with superior performance on both speed and accuracy, and proposes a new anchor densification strategy to make different types of anchors have the same density on the image, which significantly improves the recall rate of small faces.

TinaFace: Strong but Simple Baseline for Face Detection

There is no gap between face detection and generic object detection and a strong but simple baseline method to deal with face detection named TinaFace is provided, which exceeds most of the recent face detectors with larger backbone.

WIDER FACE: A Face Detection Benchmark

There is a gap between current face detection performance and the real world requirements, and the WIDER FACE dataset, which is 10 times larger than existing datasets is introduced, which contains rich annotations, including occlusions, poses, event categories, and face bounding boxes.

RetinaFace: Single-stage Dense Face Localisation in the Wild

A robust single-stage face detector, named RetinaFace, which performs pixel-wise face localisation on various scales of faces by taking advantages of joint extra-supervised and self-super supervised multi-task learning.

Group Sampling for Scale Invariant Face Detection

A group sampling method which divides the anchors into several groups according to the scale, and ensures that the number of samples for each group is the same during training, is proposed, able to advance the state-of-the-arts in face detection.

BFBox: Searching Face-Appropriate Backbone and Feature Pyramid Network for Face Detector

  • Yang LiuXu Tang
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
A FPN-attention module is proposed to joint search the architecture of backbone and FPN and comprehensive experiments on popular bench-marks, including Wider Face, FDDB, AFW and PASCALFace, display the superiority of the proposed method.

Robust Real-Time Face Detection

A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.

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

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,

FaceNet: A unified embedding for face recognition and clustering

A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.