Learning A Metric Embedding For Face Recognition Using The Multibatch Method

Abstract

This work is motivated by the engineering task of achieving a near state-of-the-art face recognition on a minimal computing budget running on an embedded system. Our main technical contribution centers around a novel training method, called Multibatch, for similarity learning, i.e., for the task of generating an invariant "face signature" through training pairs of "same" and "not-same" face images. The Multibatch method first generates signatures for a mini-batch of \(k\) face images and then constructs an unbiased estimate of the full gradient by relying on all \(k^2-k\) pairs from the mini-batch. We prove that the variance of the Multibatch estimator is bounded by \(O(1/k^2)\), under some mild conditions. In contrast, the standard gradient estimator that relies on random \(k/2\) pairs has a variance of order \(1/k\). The smaller variance of the Multibatch estimator significantly speeds up the convergence rate of stochastic gradient descent. Using the Multibatch method we train a deep

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytadmor2016learning

Related papers

• Learning Intra-batch Connections For Deep Metric Learning (2021)0.00
• Adaptive Cross Batch Normalization For Metric Learning (2023)0.00
• Dual-triplet Metric Learning For Unsupervised Domain Adaptation In Video-based Face Recognition (2020)5.84
• Triplet Similarity Embedding For Face Verification (2016)0.00
• Learning With Batch-wise Optimal Transport Loss For 3D Shape Recognition (2019)10.48
• Scaleface: Uncertainty-aware Deep Metric Learning (2022)2.26
• Unique Faces Recognition In Videos (2020)6.77
• Cp-mtml: Coupled Projection Multi-task Metric Learning For Large Scale Face Retrieval (2016)11.67