• Corpus ID: 227209466

TinaFace: Strong but Simple Baseline for Face Detection

@article{Zhu2020TinaFaceSB,
  title={TinaFace: Strong but Simple Baseline for Face Detection},
  author={Yanjia Zhu and Hongxiang Cai and Shuhan Zhang and Chenhao Wang and Yichao Xiong},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.13183}
}
Face detection has received intensive attention in recent years. Many works present lots of special methods for face detection from different perspectives like model architecture, data augmentation, label assignment and etc., which make the overall algorithm and system become more and more complex. In this paper, we point out that \textbf{there is no gap between face detection and generic object detection}. Then we provide a strong but simple baseline method to deal with face detection named… 

Figures and Tables from this paper

Going Deeper Into Face Detection: A Survey

TLDR
A detailed overview of some of the most representative deep learning based face detection methods by grouping them into a few major categories, and presenting their core architectural designs and accuracies on popular benchmarks is provided.

An Efficient Anchor-Free Face Detector with Attention Mechanisms

TLDR
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.

YOLO5Face: Why Reinventing a Face Detector

TLDR
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.

Sample and Computation Redistribution for Efficient Face Detection

TLDR
It is pointed out that training data sampling and computation distribution strategies are the keys to efficient and accurate face detection and two simple but effective methods are introduced: Sample Redistribution (SR) and Computation Redist distribution (CR), which reallocates the computation between the backbone, neck and head of the model, based on a meticulously defined search methodology.

Safe Fakes: Evaluating Face Anonymizers for Face Detectors

TLDR
The first empirical study on the effect of image anonymization on supervised training of face detectors is presented, and the best-performing GAN, DeepPrivacy, removes identifiable faces for a face detector trained on anonymized data.

Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition

. Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity

Accelerated Inference of Face Detection under Edge-Cloud Collaboration

TLDR
This paper adopts a two-step acceleration strategy for the CenterNet model that achieves a 62.12% reduction in inference latency compared to the state-of-the-art object detection model Blazeface.

Image Grid Recognition and Regression for Fast and Accurate Face Detection

TLDR
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.

FH-YOLOv4 with Constrained Aspect Ratio Loss for Video Face Detection and Public Safety

TLDR
The constrained aspect ratio loss (CARLoss) is introduced for better facial boxes regression and incorporated into the modified FH-YOLOv4, then the IoU Tracker-based video face image deduplication algorithm is proposed on the detection level.

Towards Large-Scale Small Object Detection: Survey and Benchmarks

TLDR
Two large-scale Small Object Detection dAtasets (SODA), SODA-D and S ODA-A, which focus on the Driving and Aerial scenarios respectively are constructed, and the performance of mainstream methods on SOD a is evaluated.

References

SHOWING 1-10 OF 64 REFERENCES

WIDER FACE: A Face Detection Benchmark

TLDR
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.

DSFD: Dual Shot Face Detector

TLDR
A novel detection network named Dual Shot face Detector (DSFD) is proposed which inherits the architecture of SSD and introduces a Feature Enhance Module (FEM) for transferring the original feature maps to extend the single shot detector to dual shot detector.

Accurate Face Detection for High Performance

TLDR
This report applies the Intersection over Union (IoU) loss function for regression, employ the two-step classification and regression for detection, revisit the data augmentation based on data-anchor-sampling for training, utilize the max-out operation for classification and use the multi-scale testing strategy for inference.

Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision

TLDR
A novel single-shot face detection network, named DF$2$S$^2$ (Detection with Feature Fusion and Segmentation Supervision), which introduces a more effective feature fusion pyramid and a more efficient segmentation branch on ResNet-50 to handle mentioned problems.

Aggregate channel features for multi-view face detection

TLDR
Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB test-sets, while runs at 42 FPS on VGA images.

Robust and High Performance Face Detector

TLDR
This report reimplements the state-of-the-art detector SRN and applies some tricks proposed in the recent literatures to obtain an extremely strong face detector, named VIM-FD, which achieves state of theart performance over the most popular and challenging face detection benchmark, i.e., WIDER FACE.

PyramidBox: A Context-assisted Single Shot Face Detector

TLDR
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.

PyramidBox++: High Performance Detector for Finding Tiny Face

TLDR
Improve each part of PyramidBox++ to further boost the performance, including Balanced-data-anchor-sampling, Dual-PyramidAnchors and Dense Context Module, which achieves state-of-the-art performance in hard set.

EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD),less than 0.1 million, as well as achieving comparable performance to deep heavy

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,
...