Deep Boosting Multi-Modal Ensemble Face Recognition with Sample-Level Weighting

TL;DR

This paper introduces a multi-model boosting approach with sample-level weighting for face recognition, improving robustness on hard samples and outperforming state-of-the-art methods across multiple datasets.

Contribution

It proposes a novel sample-level weighting technique inspired by AdaBoost, enhancing deep face recognition by focusing on sample hardness during training.

Findings

Superior performance on multiple face recognition datasets.

Effective handling of hard samples through model ensemble.

Analytical insights into sample mining effects on loss functions.

Abstract

Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability. However, the current training benchmarks exhibit an imbalanced quality distribution; most images are of high quality. This poses issues for generalization on hard samples since they are underrepresented during training. In this work, we employ the multi-model boosting technique to deal with this issue. Inspired by the well-known AdaBoost, we propose a sample-level weighting approach to incorporate the importance of different samples into the FR loss. Individual models of the proposed framework are experts at distinct levels of sample hardness. Therefore, the combination of models leads to a robust feature extractor without losing the discriminability on the easy samples. Also, for incorporating the sample hardness into the training criterion, we analytically show the effect of sample mining on the important aspects of current angular margin loss functions, i.e., margin and scale. The proposed method shows superior performance in comparison with the state-of-the-art algorithms in extensive experiments on the CFP-FP, LFW, CPLFW, CALFW, AgeDB, TinyFace, IJB-B, and IJB-C evaluation datasets.