Semi-Siamese Training for Shallow Face Learning

07/16/2020
by   Hang Du, et al.
7

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, i.e. only two face images are available for each ID. We define this situation as Shallow Face Learning, and find it problematic with existing training methods. Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.

READ FULL TEXT
research
05/10/2021

Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning

With the recent development of deep convolutional neural networks and la...
research
04/14/2021

Towards NIR-VIS Masked Face Recognition

Near-infrared to visible (NIR-VIS) face recognition is the most common c...
research
06/08/2018

Large-scale Bisample Learning on ID vs. Spot Face Recognition

In many face recognition applications, there is large amount of face dat...
research
05/24/2022

SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition

Deep face recognition has achieved great success due to large-scale trai...
research
05/24/2023

FaceFusion: Exploiting Full Spectrum of Multiple Datasets

The size of training dataset is known to be among the most dominating as...
research
08/06/2019

Bag of Negatives for Siamese Architectures

Training a Siamese architecture for re-identification with a large numbe...
research
07/27/2016

MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition

In this paper, we design a benchmark task and provide the associated dat...

Please sign up or login with your details

Forgot password? Click here to reset