FaceFusion: Exploiting Full Spectrum of Multiple Datasets

05/24/2023
by   Chiyoung Song, et al.
0

The size of training dataset is known to be among the most dominating aspects of training high-performance face recognition embedding model. Building a large dataset from scratch could be cumbersome and time-intensive, while combining multiple already-built datasets poses the risk of introducing large amount of label noise. We present a novel training method, named FaceFusion. It creates a fused view of different datasets that is untainted by identity conflicts, while concurrently training an embedding network using the view in an end-to-end fashion. Using the unified view of combined datasets enables the embedding network to be trained against the entire spectrum of the datasets, leading to a noticeable performance boost. Extensive experiments confirm superiority of our method, whose performance in public evaluation datasets surpasses not only that of using a single training dataset, but also that of previously known methods under various training circumstances.

READ FULL TEXT

page 3

page 5

page 11

research
01/14/2021

DAIL: Dataset-Aware and Invariant Learning for Face Recognition

To achieve good performance in face recognition, a large scale training ...
research
06/26/2014

Deep Learning Multi-View Representation for Face Recognition

Various factors, such as identities, views (poses), and illuminations, a...
research
06/21/2022

SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data

Recent deep face recognition models proposed in the literature utilized ...
research
07/16/2020

Semi-Siamese Training for Shallow Face Learning

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, pr...
research
08/03/2021

Domain Adaptor Networks for Hyperspectral Image Recognition

We consider the problem of adapting a network trained on three-channel c...
research
01/11/2022

Boosting Video Representation Learning with Multi-Faceted Integration

Video content is multifaceted, consisting of objects, scenes, interactio...

Please sign up or login with your details

Forgot password? Click here to reset