Training deep neural networks for image recognition often requires large-scale human annotated data. To reduce the reliance of deep neural solutions on labeled data, state-of-the-art semi-supervised methods have been proposed in the literature. Nonetheless, the use of such semi-supervised methods has been quite rare in the field of facial expression recognition (FER). In this paper, we present a comprehensive study on recently proposed state-of-the-art semi-supervised learning methods in the context of FER. We conduct comparative study on eight semi-supervised learning methods, namely Pi-Model, Pseudo-label, Mean-Teacher, VAT, MixMatch, ReMixMatch, UDA, and FixMatch, on three FER datasets (FER13, RAF-DB, and AffectNet), when various amounts of labeled samples are used. We also compare the performance of these methods against fully-supervised training. Our study shows that when training existing semi-supervised methods on as little as 250 labeled samples per class can yield comparable performances to that of fully-supervised methods trained on the full labeled datasets. To facilitate further research in this area, we make our code publicly available at: https://github.com/ShuvenduRoy/SSL_FER
翻译:为了减少深层神经解决方案对标签数据的依赖,文献中提出了最先进的半监督方法。然而,在面部表达识别领域,使用这种半监督方法的情况相当少见。在本文件中,我们提交了一份关于最近在FER背景下拟议的最新最先进半监督学习方法的综合研究报告。我们开展了关于八种半监督学习方法的比较研究,即Pi-Model、Pseudo-label、May-Teacher、VAT、MixMatch、ReMixMatch、UDA和FixMatch等八种半监督方法,在使用各种数量标签样本时,使用这种半监督方法(FER13、RAF-DB和AfectNet)。我们还比较了这些方法的绩效和完全监督培训。我们的研究显示,在将现有的半监督方法培训成小为250个标签样本时,VAT、MixMatch、ReixMatch、ReixMatch、UDA和FixMatch等, 在三种FERS数据集(F13、RAF-DB和AffectNet)的使用中,当使用各种标签样本时,我们所培训的完全监督/ComfectSSS。