.png){kind=icon}
返回
Face recognition with dense supervision
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2019.12.052.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent advances in face recognition mostly concentrate on designing more discriminative loss functions or adding normalization on features/weights to make a single feature more accurate. In this work, inspired by the frequently used multi-patch ensemble method for face recognition and part-based models for person re-identification, we propose a novel training strategy to enhance the discriminability of deeply learned feature from another perspective, namely learning with dense supervision. The main idea is to apply multiple classification losses on top of multiple component features extracted from a single network. Ideally, each component feature is expected to be accurate and have low correlation with the others. To this end, we first design a metric called feature consistency to evaluate the correlation between one component feature and the others, which is defined as the sum of distances between one component feature and the others, where the distance here is measured with KL divergence between corresponding softmax probabilities. Then we use feature consistency to select which component features to sample for one learning pass by importance sampling. The dense supervision significantly outperforms the single supervision baseline and even performs on par with its multi-patch ensemble counterpart which has much more parameters (9x). Our experimental results match state-of-the-art performance on LFW, YTF, MegaFace and surpass the others on LFW BLUFR and VGGFace2 pose protocol, thereby achieving state-of-the-art. Specially, results on VGGFace2 also show the superiority of the dense supervision on cross-pose face matching. Communicated by Dr Zhen Lei Keywords: Face recognition Dense supervision Feature consistency Importance sampling (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Face recognition
Dense supervision
Feature consistency
Importance sampling
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Stream loss: ConvNet learning for face verification using unlabeled videos in the wild.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏
Combining multilevel feature extraction and multi-loss learning for person re-identificationNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容