Abstract
Inspired by the effectiveness of adversarial training in the area of Generative Adversarial Networks we present a new approach for learning feature representations in person re-identification. We investigate different types of bias that typically occur in re-ID scenarios, i.e., pose, body part and camera view, and propose a general approach to address them. We introduce an adversarial strategy for controlling bias, named Bias-controlled Adversarial framework (BCA), with two complementary branches to reduce or to enhance bias-related features. The results and comparison to the state of the art on different benchmarks show that our framework is an effective strategy for person re-identification. The performance improvements are in both full and partial views of persons.
Abstract (translated)
在生成性对抗网络领域的对抗训练效果的启发下,我们提出了一种新的学习特征表示的方法。我们研究了不同类型的偏差,通常发生在RE ID场景中,即姿势、身体部位和摄像头视图,并提出了一种解决这些偏差的一般方法。我们介绍了一种控制偏差的对抗策略,称为偏差控制对抗框架(BCA),它有两个互补的分支来减少或增强与偏差相关的特性。结果表明,我们的框架是一种有效的人员重新识别策略。绩效的提高体现在人的全部和部分观点上。
URL
https://arxiv.org/abs/1904.00244