NormFace: L2 Hypersphere Embedding for Face Verification
Thanks to the recent developments of Convolutional Neural Networks, the performance of face verification methods has increased rapidly. In a typical face verification method, feature normalization is a critical step for boosting performance. This motivates us to introduce and study the effect of normalization during training. But we find this is non-trivial, despite normalization being differentiable. We identify and study four issues related to normalization through mathematical analysis, which yields understanding and helps with parameter settings. Based on this analysis we propose two strategies for training using normalized features. The first is a modification of softmax loss, which optimizes cosine similarity instead of inner-product. The second is a reformulation of metric learning by introducing an agent vector for each class. We show that both strategies, and small variants, consistently improve performance by between 0.2% to 0.4% on the LFW dataset based on two models. This is significant because the performance of the two models on LFW dataset is close to saturation at over 98%. Codes and models are released on https://github.com/happynear/NormFace
Code (3)
Tasks
Face VerificationMetric LearningSimilar Papers 제목 키워드 기반
Hypersphere Face Uncertainty Learning
An emerging line of research has found that \emph{hyperspherical} spaces better match the underlying geometry of facial images, as evidenced by the state-of-the-art facial recognition methods which benefit empirically fr…
Face VerificationHarnessing Unrecognizable Faces for Improving Face Recognition
The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector. When the detector succeeds, it can detec…
Face RecognitionQuantizationOn Manifold Hypothesis: Hypersurface Submanifold Embedding Using Osculating Hyperspheres
Consider a set of $n$ data points in the Euclidean space $\mathbb{R}^d$. This set is called dataset in machine learning and data science. Manifold hypothesis states that the dataset lies on a low-dimensional submanifold …
Dimensionality ReductionFew-shot Classification with Hypersphere Modeling of Prototypes
Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, …
ClassificationFew-Shot LearningMeta-LearningRepresentation LearningnGPT: Normalized Transformer with Representation Learning on the Hypersphere
We propose a novel neural network architecture, the normalized Transformer (nGPT) with representation learning on the hypersphere. In nGPT, all vectors forming the embeddings, MLP, attention matrices and hidden states ar…
Representation Learning