arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.04567cs.CV
收藏

BoundaryFace:一个基于噪声标签自校正的人脸识别挖掘框架

BoundaryFace: A mining framework with noise label self-correction for Face Recognition

Southwest Jiaotong University(西南交通大学)

Shijie Wu, Xun Gong

摘要:

近年来,由于损失函数的进步和训练集规模的爆炸式增长,人脸识别取得了巨大的进展。一个适当的设计损失被视为关键,以提取判别特征进行分类。已经提出了几种基于边缘的损失作为人脸识别中softmax损失的替代方案。然而,还有两个问题需要考虑:1)他们忽视了硬样本挖掘对判别学习的重要性。2)标签噪声普遍存在于大规模数据集中,严重影响模型的性能。在本文中,从决策边界的角度出发,我们提出了一个新的挖掘框架,侧重于一个样本的地面真值类中心和最近的负类中心之间的关系。具体而言,提出了一种闭集噪声标签自校正模块,使该框架能够很好地处理包含大量标签噪声的数据集。所提出的方法在各种人脸识别基准测试中始终优于SOTA方法。培训代码已在https://github.com/SWJTU-3DVision/BoundaryFace上发布。

英文摘要:

Face recognition has made tremendous progress in recent years due to the advances in loss functions and the explosive growth in training sets size. A properly designed loss is seen as key to extract discriminative features for classification. Several margin-based losses have been proposed as alternatives of softmax loss in face recognition. However, two issues remain to consider: 1) They overlook the importance of hard sample mining for discriminative learning. 2) Label noise ubiquitously exists in large-scale datasets, which can seriously damage the model's performance. In this paper, starting from the perspective of decision boundary, we propose a novel mining framework that focuses on the relationship between a sample's ground truth class center and its nearest negative class center. Specifically, a closed-set noise label self-correction module is put forward, making this framework work well on datasets containing a lot of label noise. The proposed method consistently outperforms SOTA methods in various face recognition benchmarks. Training code has been released at https://github.com/SWJTU-3DVision/BoundaryFace.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑