Detecting small faces in the wild based on generative adversarial network and contextual information. (October 2019)

• Record Type: Journal Article
• Authors: Zhang, Yongqiang; Ding, Mingli; Bai, Yancheng; Ghanem, Bernard
• Is Part Of: Pattern recognition. Volume 94(2019:Oct.)
• Page Start: 74
• Page End: 86
• Publication Date: 2019-10
• Subjects: Face detection -- Tiny faces -- Super-resolution -- Generative adversarial network -- Contextual information; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.023
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel unified end-to-end convolutional neural network architecture for small face detection is proposed. A regression branch is introduced to the GAN-based architecture for further refining the locations of small faces in the wild. New losses are designed to train the GAN-based network for small face detection in the wild. Contextual information around face regions is further utilized to detect hard faces in the real-world scenarios. The performance of our method outperforms previous state-of-the-art approaches by a large margin on WIDER FACE dataset, especially on the most challenging Hard subset. Abstract: Face detection techniques have been developed for decades, and one of the remaining open challenges is detecting small faces in unconstrained conditions. The reason is that tiny faces are often lacking detailed information and blurry. In this paper, we proposed an algorithm to directly generate a clear high-resolution face from a small blurry one by adopting a generative adversarial network (GAN). Toward this end, the basic GAN formulation achieves it by super-resolving and refining sequentially ( e.g. SR-GAN and Cycle-GAN). However, we design a novel network to address the problem of super-resolving and refining jointly. Moreover, we also introduce new training losses ( i.e. classification loss and regression loss) to promote the generator network to recover fine details of the small faces and to guide the discriminator network to distinguish face vs. non-face and to refine location simultaneously. Additionally, considering the importance of contextual information when detecting tiny faces in crowded cases, the context around face regions is combined to train the proposed GAN-based network for mining those very small faces from unconstrained scenarios. Extensive experiments on the challenging datasets WIDER FACE and FDDB demonstrate the effectiveness of the proposed method in restoring a clear high-resolution face from a small blurry one, and show that the achieved performance outperforms previous state-of-the-art methods by a large margin.