DeepAI AI Chat
Log In Sign Up

Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors

by   Petru Soviany, et al.

Although deep neural networks offer better face detection results than shallow or handcrafted models, their complex architectures come with higher computational requirements and slower inference speeds than shallow neural networks. In this context, we study five straightforward approaches to achieve an optimal trade-off between accuracy and speed in face detection. All the approaches are based on separating the test images in two batches, an easy batch that is fed to a faster face detector and a difficult batch that is fed to a more accurate yet slower detector. We conduct experiments on the AFW and the FDDB data sets, using MobileNet-SSD as the fast face detector and S3FD (Single Shot Scale-invariant Face Detector) as the accurate face detector, both models being pre-trained on the WIDER FACE data set. Our experiments show that the proposed difficulty metrics compare favorably to a random split of the images.


Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction

There are mainly two types of state-of-the-art object detectors. On one ...

YOLO5Face: Why Reinventing a Face Detector

Tremendous progress has been made on face detection in recent years usin...

Dockerface: an easy to install and use Faster R-CNN face detector in a Docker container

Face detection is a very important task and a necessary pre-processing s...

Bootstrapping Face Detection with Hard Negative Examples

Recently significant performance improvement in face detection was made ...

LFFD: A Light and Fast Face Detector for Edge Devices

Face detection, as a fundamental technology for various applications, is...

FDDB-360: Face Detection in 360-degree Fisheye Images

360-degree cameras offer the possibility to cover a large area, for exam...

Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors

Object detection aims at high speed and accuracy simultaneously. However...