This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image. However, traditional data augmentation may bring to the fore undesirable distortions on identity features, which is not always favorable in id-sensitive ReID tasks. In this paper, we propose to replace traditional data augmentation with a generative adversarial network (GAN) that is targeted to generate augmented views for contrastive learning. A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. Deviating from previous GAN-based ReID methods that only work in id-unrelated space (pose and camera style), we conduct GAN-based augmentation on both id-unrelated and id-related features. We further propose specific contrastive losses to help our network learn invariance from id-unrelated and id-related augmentations. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks.
翻译:这项工作的重点是在个人身份再识别方面进行不受监督的代表性学习(ReID)。最近自我监督的对比式学习方法通过尽量扩大同一图像两种增强的视角之间的相似性来学习差异性。然而,传统的数据增强可能会对身份特征造成不可取的扭曲,而这种扭曲并非始终有利于对身份敏感 ReID的任务。在本文件中,我们提议用一个基因化的对立网络(GAN)来取代传统的数据增强,目的是为对比性学习产生更多的观点。一个3D网形导人图像生成器建议将一个人的图像分解成与身份相关和与身份无关的特征。我们的方法偏离了以前基于GAN的仅对与身份无关的空间(定位和摄像风格)起作用的基于GAN的对身份特征的重新识别方法,我们在与身份无关和与身份相关的特点上都进行了基于GAN的增强。我们进一步提出了具体的对比性损失,以帮助我们的网络从与身份无关和与身份相关增强有关的观点中学习。我们的方法通过联合培训基因化和对比性化模块,从而在新的国家主流业绩基准上实现新的不受监督。