Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering
This work addresses face recognition for computer vision applications, presenting an incremental improvement by combining clustering with traditional methods.
The paper tackles the problem of improving face recognition by integrating clustering knowledge through a joint optimization of label classification and supervised contrastive clustering, resulting in demonstrated effectiveness and superiority over existing approaches on facial benchmarks.
Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint optimization task of label classification and supervised contrastive clustering to introduce the cluster knowledge to the traditional face recognition task in two ways. We first extend ArcFace with a cluster-guided angular margin to adjust the within-class feature distribution according to the hard level of face clustering. Secondly, we propose a supervised contrastive clustering approach to pull the features to the cluster center and propose the cluster-aligning procedure to align the cluster center and the learnable class center in the classifier for joint training. Finally, extensive qualitative and quantitative experiments on popular facial benchmarks demonstrate the effectiveness of our paradigm and its superiority over the existing approaches to face recognition.