Joint Segmentation and Identification Feature Learning for Occlusion Face Recognition

The existing occlusion face recognition algorithms almost tend to pay more attention to the visible facial components. However, these models are limited because they heavily rely on existing face segmentation approaches to locate occlusions, which is extremely sensitive to the performance of mask learning. To tackle this issue, we propose a joint segmentation and identification feature learning framework for end-to-end occlusion face recognition. More particularly, unlike employing an external face segmentation model to locate the occlusion, we design an occlusion prediction module supervised by known mask labels to be aware of the mask. It shares underlying convolutional feature maps with the identification network and can be collaboratively optimized with each other. Furthermore, we propose a novel channel refinement network to cast the predicted single-channel occlusion mask into a multi-channel mask matrix with each channel owing a distinct mask map. Occlusion-free feature maps are then generated by projecting multi-channel mask probability maps onto original feature maps. Thus, it can suppress the representation of occlusion elements in both the spatial and channel dimensions under the guidance of the mask matrix. Moreover, in order to avoid misleading aggressively predicted mask maps and meanwhile actively exploit usable occlusion-robust features, we aggregate the original and occlusion-free feature maps to distill the final candidate embeddings by our proposed feature purification module. Lastly, to alleviate the scarcity of real-world occlusion face recognition datasets, we build large-scale synthetic occlusion face datasets, totaling up to 980193 face images of 10574 subjects for the training dataset and 36721 face images of 6817 subjects for the testing dataset, respectively. Extensive experimental results on the synthetic and real-world occlusion face datasets show that our approach significantly outperforms the state-of-the-art in both 1:1 face verification and 1:N face identification.

I. Introduction

Deep learning has achieved a remarkable improvement in face recognition. Recent advanced convolutional neural network (CNN)-based face recognition approaches [1]–[5] favor more discriminative facial features of small intra-identity distances and large interidentity distances. These methods have been successfully applied to various real-world applications. Despite the huge progress on regular benchmarks of normal or slightly occluded faces, state-of-the-art models still struggle under severe occlusions. Faces are usually masked by various occlusions in real-world scenarios, such as sunglasses, masks, scarves, and so on. For instance, wearing a mask has become increasingly popular during the COVID-19 coronavirus epidemic. Because occlusions conceal the available landmarks of the face, the face recognition performance on randomly occluded faces is far from satisfactory. Handling occlusions in face recognition becomes a crucial challenge.