Semi-Siamese Training for Shallow Face Learning
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. $\textit{We define this situation as Shallow Face Learning, and find it problematic with existing training methods.}$ 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.
Code (3)
Tasks
Face RecognitionSimilar Papers 제목 키워드 기반
Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
With the recent development of deep convolutional neural networks and large-scale datasets, deep face recognition has made remarkable progress and been widely used in various applications. However, unlike the existing pu…
Face RecognitionSiamese Graph Learning for Semi-supervised Age Estimation
In this paper, we propose a Siamese graph learning (SGL) approach to alleviate aging dataset bias. While numerous semi-supervised algorithms have been successfully applied to classification tasks, most of them assume tha…
Age EstimationDiversityGraph LearningSemi-Supervised Learning using Siamese Networks
Neural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully fo…
VirFace: Enhancing Face Recognition via Unlabeled Shallow Data
Recently, exploiting the effect of the unlabeled data for face recognition attracts increasing attention. However, there are still few works considering the situation that the unlabeled data is shallow which widely e…
Face RecognitionRegistration of Multiresolution Remote Sensing Images Based on L2-Siamese Model
The registration of multiresolution optical remote sensing images has been widely used in image fusion, change detection, and image stitching. However, traditional registration methods achieve poor accuracy in the regist…
AttributeChange DetectionImage RegistrationImage Stitching