Adversarial Erasing Attention for Person Re-Identification in Camera Networks Under Complex Environments

Abstract

Person re-identification (Re-ID) in camera networks under complex environments has achieved promising performance using deep feature representations. However, most approaches usually ignore to learn features from non-salient parts of pedestrian, which results in an incomplete pedestrian representation. In this paper, we propose a novel person Re-ID method named Adversarial Erasing Attention (AEA) to mine discriminative completed features using an adversarial way. Specifically, the proposed AEA consists of the basic network and the complementary network. On the one hand, original pedestrian images are used to train the basic network in order to extract global and local deep features. On the other hand, to learn features complementary to the basic network, we propose the adversarial erasing operation, that locates non-salient areas with the help of attention map, to generate erased pedestrian images. Then, we utilize them to train the complementary network and adopt the dynamic strategy to match the dynamic status of AEA in the learning process. Hence, the diversity of training samples is enriched and the complementary network could discover new clues when learning deep features. Finally, we combine the features learned from the basic and complementary networks to represent the pedestrian image. Experiments on three databases (Market1501, CUHK03 and DukeMTMC-reID) demonstrate the proposed AEA achieves great performances. INDEX TERMS Person re-identification, dynamic strategy, adversarial learning. I. INTRODUCTION Person re-identification (Re-ID) in camera networks targets to retrieve a specific pedestrian from a large gallery which is captured by multiple visual sensors [1]-[3]. There are many applications (such as multi-camera tracking [4], [5], crowd counting [6], [7] and so on [8], [9]) that require an accurate person Re-ID algorithm. However, it is a challenging task under complex environments because of significant changes in body poses, viewpoints, illuminations, etc. Recently, many researchers [10]-[14] employ Convolutional Neural Networks (CNNs) to extract pedestrian The associate editor coordinating the review of this manuscript and approving it for publication was Qilian Liang .

A Novel Pedestrian Reidentification Method Based on a Multiview Generative Adversarial Network

“…This method achieved the latest results at that time. Liu et al [43] proposed a novel PRI method, namely, Adversarial Erasing Attention (AEA), to use adversarial method to mine the complete features of differences. Guo et al [44] propose a method for group-shuffling dual random walks with label smoothing.…”

Temporal Complementary Learning for Video Person Re-Identification

“…Recently, Liu et al [24,25] also propose to use saliency to guide erasing to learn complementary features. However, the purpose and implementation of these methods are different from ours.…”

Stochastic attentions and context learning for person re-identification

“…These techniques are robust with no additional overhead on any baseline model and quickly train the model. Although these random drop based techniques improve the performances of Baseline models but more sophisticated ways to learn both the highly discriminative and less discriminative parts of the images are proposed by ( Li & Xu, 2020 ; Liu et al, 2020 ; Perwaiz, Fraz & Shahzad, 2019 ). These multi-streams attention branches captures the discriminant attention features at different level but these approaches are quite expensive in terms of computations.…”