类别特征约束的多目标域表情识别方法

Multi-target domain facial expression recognition based on class-wise feature constraint

表情识别FER方法通常会受到采集环境和受试者区域、种族等因素的影响。为了提升FER方法的泛化性能,无监督的域自适应表情识别方法UDA-FER成为了研究热点。现有的UDA-FER方法普遍存在2个问题:(1)仅关注对目标域的识别率,导致方法从源域迁移至目标域后,对源域的识别率急剧下降;(2)仅研究基于单个目标域的UDA-FER方法,将现有方法直接应用于多个目标域会导致方法识别率骤降。为解决上述问题,提出了一种类别特征约束的多目标域表情识别方法MTD-FER,实现FER向多个目标域的连续迁移。为了保持对源域的识别率并提高对多个目标域的识别率,MTD-FER设计了类别自适应的伪标签标记CAPL模块和类别特征约束CWFC模块,挑选目标域高质量的样本标记为伪标签,并对齐各个域同类样本的特征,缓解连续迁移导致的灾难性遗忘问题。以RAF-DB为源域,FER-2013和ExpW为目标域,进行大量的实验,证明了MTD-FER的有效性。实验结果表明,与基准方法相比,MTD-FER在多次迁移后,源域识别率提升6.36%,与迁移之前基本持平;在各个目标域性能均有所提升,其中FER-2013性能提升了27.33%,ExpW性能提升了3.03%。

Facial Expression Recognition(FER)is usually affected by the collected environment,regions,race,and other factors.In order to improve the generalization of FER methods,Unsupervised Domain Adaption Facial Expression Recognition(UDA-FER)algorithms have attracted more and more attentions.Existing UDA-FER algorithms generally suffer from two issues:(1)they care more about the performance in the target domain,resulting in a sharp drop in the performance of the source domain after transferring from the source to the target domain;(2)They are just appropriate for the case of the single target domain.The UDA-FER methods will show terrible performance when applying it to multiple target domains directly.To solve the above issues,a Multi-Target Domain Facial Expression Recognition method based on class-wise feature constraint(MTD-FER)is proposed,which supports the FER methods transferring to multiple target domains in succession and ensures the methods retains a better recognition rate on each domain.To this end,MTD-FER designs the Class-Adaptive Pseudo Label methods(CAPL)and Class-Wise Feature Constraint mothods(CWFC),which learn pseudo labels for samples with high quality in target domains and align each class of features from disparate domains,so as to alleviate the issue of catastrophic forgetting resulting from domain transferring.Through extensive experiments using RAF-DB as the source domain and FER-2013 and ExpW as the target domains,the effectiveness of the MTD-FER algorithm is demonstrated.Experimental results show that,compared with the baseline method,MTD-FER improves the performance in the source domain by 6.36%,which is on par with the methods before transferring to target domains,and improves the performance by 27.33% and 3.03%in two target domains,respectively.