GhostVLAD for set-based face recognition

10/23/2018
by   Yujie Zhong, et al.
0

The objective of this paper is to learn a compact representation of image sets for template-based face recognition. We make the following contributions: first, we propose a network architecture which aggregates and embeds the face descriptors produced by deep convolutional neural networks into a compact fixed-length representation. This compact representation requires minimal memory storage and enables efficient similarity computation. Second, we propose a novel GhostVLAD layer that includes ghost clusters, that do not contribute to the aggregation. We show that a quality weighting on the input faces emerges automatically such that informative images contribute more than those with low quality, and that the ghost clusters enhance the network's ability to deal with poor quality images. Third, we explore how input feature dimension, number of clusters and different training techniques affect the recognition performance. Given this analysis, we train a network that far exceeds the state-of-the-art on the IJB-B face recognition dataset. This is currently one of the most challenging public benchmarks, and we surpass the state-of-the-art on both the identification and verification protocols.

READ FULL TEXT
research
03/17/2016

Neural Aggregation Network for Video Face Recognition

This paper presents a Neural Aggregation Network (NAN) for video face re...
research
03/26/2020

Compact Deep Aggregation for Set Retrieval

The objective of this work is to learn a compact embedding of a set of d...
research
07/30/2018

Comparator Networks

The objective of this work is set-based verification, e.g. to decide if ...
research
08/27/2023

FaceCoresetNet: Differentiable Coresets for Face Set Recognition

In set-based face recognition, we aim to compute the most discriminative...
research
07/24/2018

Multicolumn Networks for Face Recognition

The objective of this work is set-based face recognition, i.e. to decide...
research
11/06/2016

Deep Convolutional Neural Network Features and the Original Image

Face recognition algorithms based on deep convolutional neural networks ...
research
12/02/2020

Artist, Style And Year Classification Using Face Recognition And Clustering With Convolutional Neural Networks

Artist, year and style classification of fine-art paintings are generall...

Please sign up or login with your details

Forgot password? Click here to reset