arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10172cs.CV
收藏

NPCFace:大规模人脸识别的正负协同训练

NPCFace: Negative-Positive Collaborative Training for Large-scale Face Recognition

Shanghai University(上海大学);JD AI Research(京东AI研究院);National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所模式识别国家实验室)

Dan Zeng, Hailin Shi, Hang Du, Jun Wang, Zhen Lei, Tao Mei

摘要:

在过去的几年里,深度人脸识别的训练方案有了很大的发展,但它在大规模数据情况下遇到了新的挑战,大量和多样化的困难情况发生。特别是在低错误接受率(FAR)的范围内,在阳性(类内)和阴性(类间)中都存在各种困难情况。在本文中,我们研究如何更好地利用这些硬样本,以提高训练。文献的做法,这是基于利润的制定,无论是积极的logit或负logits。然而,硬阳性和硬阴性之间的相关性被忽视,正和负logits中的边缘之间的关系也被忽视。我们发现这种相关性是显著的,特别是在大规模数据集中,人们可以利用它来通过将每个训练样本的正边缘和负边缘相关联来提高训练。为此,我们建议在样本范围内明确正负利润率之间的合作。在给定一批硬样本的情况下,提出了一种新的负-正协作损失模型NPCFace,该模型通过softmax logits中的协作边缘机制,强调了对负-正硬样本的训练,同时也更好地解释了负-正硬度相关性。此外,重点是实施与改进的公式,以实现稳定的收敛性和灵活的参数设置。我们验证了我们的方法的有效性在各种基准的大规模人脸识别,并获得有利的结果,特别是在低FAR范围。

英文摘要:

The training scheme of deep face recognition has greatly evolved in the past years, yet it encounters new challenges in the large-scale data situation where massive and diverse hard cases occur. Especially in the range of low false accept rate (FAR), there are various hard cases in both positives (intra-class) and negatives (inter-class). In this paper, we study how to make better use of these hard samples for improving the training. The literature approaches this by margin-based formulation in either positive logit or negative logits. However, the correlation between hard positive and hard negative is overlooked, and so is the relation between the margins in positive and negative logits. We find such correlation is significant, especially in the large-scale dataset, and one can take advantage from it to boost the training via relating the positive and negative margins for each training sample. To this end, we propose an explicit collaboration between positive and negative margins sample-wisely. Given a batch of hard samples, a novel Negative-Positive Collaboration loss, named NPCFace, is formulated, which emphasizes the training on both negative and positive hard cases via the collaborative-margin mechanism in the softmax logits, and also brings better interpretation of negative-positive hardness correlation. Besides, the emphasis is implemented with an improved formulation to achieve stable convergence and flexible parameter setting. We validate the effectiveness of our approach on various benchmarks of large-scale face recognition, and obtain advantageous results especially in the low FAR range.

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。

↑