DAFE-FD: Density Aware Feature Enrichment for Face Detection

Abstract

Recent research on face detection, which is focused primarily on improving accuracy of detecting smaller faces, attempt to develop new anchor design strategies to facilitate increased overlap between anchor boxes and ground truth faces of smaller sizes. In this work, we approach the problem of small face detection with the motivation of enriching the feature maps using a density map estimation module. This module, inspired by recent crowd counting/density estimation techniques, performs the task of estimating the per pixel density of people/faces present in the image. Output of this module is employed to accentuate the feature maps from the backbone network using a feature enrichment module before being used for detecting smaller faces. The proposed approach can be used to complement recent anchor-design based novel methods to further improve their results. Experiments conducted on different datasets such as WIDER, FDDB and Pascal-Faces demonstrate the effectiveness of the proposed approach.

i Effects of meteorological factors on the prediction of malaria incidences AI-based approaches i

“…Authors in (43) presented a feature space enrichment method and found improvements in classification accuracy using a new approach rather than the original feature space. In this series, Authors in (44) presented a new feature enrichment method for face detection based on density parameters. Using density awareness in features yielded better accuracy and the authors advocated the use of density-aware feature enrichment in recent anchor design-based methods.…”

HA-CCN: Hierarchical Attention-Based Crowd Counting Network

“…Considering that crowd images have large variations in head sizes, it is essential to leverage multi-scale information by employing feature maps from different conv layers of the VGG16 network [13]. Several works such as [14,15,16,17] have demonstrated that different sized objects are captured by different layers in a deep network. Hence, an obvious approach would be to design a multi-scale counting network [18,19] that concatenates feature maps from different layers of the VGG16 network.…”

Feature Extraction and Fusion for Face Recognition Systems using Pre-Trained Convolutional Neural Networks

“…The sets of the feature vector had a rich information about the raw biometric data. Combination at this level is achieved better recognition performance [5], [6]. However, fusion at this level is an important process, which provides the most discriminatory information from original various feature sets.…”