Feature Agglomeration Networks for Single Stage Face Detection

12/03/2017
by   Jialiang Zhang, et al.
0

Recent years have witnessed promising results of face detection using deep learning, especially for the family of region-based convolutional neural networks (R-CNN) methods and their variants. Despite making remarkable progresses, face detection in the wild remains an open research challenge especially when detecting faces at vastly different scales and characteristics. In this paper, we propose a novel framework of "Feature Agglomeration Networks" (FAN) to build a new single stage face detector, which not only achieves state-of-the-art performance but also runs efficiently. As inspired by the recent success of Feature Pyramid Networks (FPN) lin2016fpn for generic object detection, the core idea of our framework is to exploit inherent multi-scale features of a single convolutional neural network to detect faces of varied scales and characteristics by aggregating higher-level semantic feature maps of different scales as contextual cues to augment lower-level feature maps via a hierarchical agglomeration manner at marginal extra computation cost. Unlike the existing FPN approach, we construct our FAN architecture using a new Agglomerative Connection module and further propose a Hierarchical Loss to effectively train the FAN model. We evaluate the proposed FAN detector on several public face detection benchmarks and achieved new state-of-the-art results with real-time detection speed on GPU.

READ FULL TEXT

page 2

page 10

page 11

research
12/09/2016

Feature Pyramid Networks for Object Detection

Feature pyramids are a basic component in recognition systems for detect...
research
11/20/2018

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

The performance of face detectors has been largely improved with the dev...
research
03/27/2017

Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained "Hard Faces"

Large-scale variations still pose a challenge in unconstrained face dete...
research
03/11/2019

MSFD:Multi-Scale Receptive Field Face Detector

We aim to study the multi-scale receptive fields of a single convolution...
research
08/02/2023

ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces

The prominent progress in generative models has significantly improved t...
research
07/29/2017

Recurrent Scale Approximation for Object Detection in CNN

Since convolutional neural network (CNN) lacks an inherent mechanism to ...
research
06/15/2019

EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

In this paper, we propose a new multi-scale face detector having an extr...

Please sign up or login with your details

Forgot password? Click here to reset