论文标题
基于自适应图的特征归一化，以识别面部表达
Adaptive Graph-Based Feature Normalization for Facial Expression Recognition
论文作者
论文摘要
面部表达识别（FER）遭受了由含糊不清的面部图像和注释者主观性引起的数据不确定性，从而导致了文化语义和特征协变量转移问题。现有作品通常通过估计噪声分布或通过从干净的数据中学到的知识指导网络培训来纠正标签错误的数据，从而忽略了表达式的关联关系。在这项工作中，我们提出了一种基于自适应的特征归一化（AGFN）方法，以通过将特征分布与表达式结合进行标准化来保护FER模型免受数据不确定性。具体而言，我们提出了一个泊松图生成器，以通过采样过程在每个迷你批次中自适应地构造样品拓扑图，并相应地设计了一种坐标下降策略来优化提出的网络。我们的方法的最先进功能分别在基准数据集中的精度为91.84％和91.11％，分别为FRPLUS和RAF-DB，而错误标签的数据的百分比增加（例如20％）（例如20％），我们的网络现有的现有效果显着高达3.38％和4.52％和4.52％。
Facial Expression Recognition (FER) suffers from data uncertainties caused by ambiguous facial images and annotators' subjectiveness, resulting in excursive semantic and feature covariate shifting problem. Existing works usually correct mislabeled data by estimating noise distribution, or guide network training with knowledge learned from clean data, neglecting the associative relations of expressions. In this work, we propose an Adaptive Graph-based Feature Normalization (AGFN) method to protect FER models from data uncertainties by normalizing feature distributions with the association of expressions. Specifically, we propose a Poisson graph generator to adaptively construct topological graphs for samples in each mini-batches via a sampling process, and correspondingly design a coordinate descent strategy to optimize proposed network. Our method outperforms state-of-the-art works with accuracies of 91.84% and 91.11% on the benchmark datasets FERPlus and RAF-DB, respectively, and when the percentage of mislabeled data increases (e.g., to 20%), our network surpasses existing works significantly by 3.38% and 4.52%.
