PA-GAN: A Patch-Attention Based Aggregation Network for Face Recognition in Surveillance

Abstract

Face recognition in unconstraint surveillance is a complicated problem on account of motion blur, expression variations and low resolution. Recent works have demonstrated that patch-attention is strictly more powerful than convolution in recognition models. In this study, we investigate the task of unconstraint surveillance face recognition. First, a Patch-Attention Generative Adversarial Network (PA-GAN) model is devised to aggregate some robust features on behalf of a set of raw surveillance frames, which not only increases the recognition accuracy but also reduces the computational costs of face matching. Second, an improved center loss function combined with abundant unlabeled surveillance faces is utilized to accurately classify the known identities. With the proposed method, the discriminativeness of the face representations is largely enhanced. Finally, the proposed method is verified in two widely used datasets, IJB-A dataset and QMUL-SurvFace dataset to demonstrate the effectiveness. Evaluation of the algorithm performances in comparison with other state-of-the-art methods indicates that the proposed design can achieve competitive accuracy on both the verification and identification protocols.

Redundancy Removing Aggregation Network With Distance Calibration for Video Face Recognition

“…It reconstructs a single image as output by average pooling the video frames to supervise the aggregation training. Similar practices include [21], [22], which aggregate each frame adaptively to a few representations through attention mechanism and improved loss function. In order to solve the out-of-focus blur and motion blur in video face, some schemes [23]- [25] try to employ super-resolution technique to tackle the problem.…”

3D Face Image Inpainting with Generative Adversarial Nets

“…In the field of computer vision, remarkable achievements have been made in the research and application of convolutional neural network (CNN) [6]. Inspired by the neural mechanism of animal vision, CNN network has excellent performance in machine vision and other fields [7,8].…”