Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
Jun-uk Jung (KOREATECH),* seon-hoon SH Lee (koreatech), Heung-Seon Oh (KOREATECH), Yong-Jun Park (KOREATECH), Sung-Bin Son (KOREATECH), Joo-chan Park (KOREATECH)
The 33rd British Machine Vision Conference
Abstract
The goal of face recognition (FR) can be viewed as a pair similarity optimization problem, maximizing a similarity set $\mathcal{S}^p$ over positive pairs, while minimizing similarity set $\mathcal{S}^n$ over negative pairs. Ideally, it is expected that FR models form a well-discriminative feature space (WDFS) that satisfies $\inf{\mathcal{S}^p} > \sup{\mathcal{S}^n}$. With regard to WDFS, the existing deep feature learning paradigms (i.e., metric and classification losses) can be expressed as a unified perspective on different pair generation (PG) strategies. Unfortunately, in the metric loss (ML), it is infeasible to generate negative pairs taking all classes into account in each iteration because of the limited mini-batch size. In contrast, in classification loss (CL), it is difficult to generate extremely hard negative pairs owing to the convergence of the class weight vectors to their center. This leads to a mismatch between the two similarity distributions of the sampled pairs and all negative pairs. Thus, this paper proposes a unified negative pair generation (UNPG) by combining two PG strategies (i.e., MLPG and CLPG) from a unified perspective to alleviate the mismatch. UNPG introduces useful information about negative pairs using MLPG to overcome the CLPG deficiency. Moreover, it includes filtering the similarities of noisy negative pairs to guarantee reliable convergence and improved performance. Exhaustive experiments show the superiority of UNPG by achieving state-of-the-art performance across recent loss functions on public benchmark datasets.Video
Citation
@inproceedings{Jung_2022_BMVC,
author = {Jun-uk Jung and seon-hoon SH Lee and Heung-Seon Oh and Yong-Jun Park and Sung-Bin Son and Joo-chan Park},
title = {Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0421.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by