Domain Invariant Noise-Tolerant Learning for Unsupervised Cross-Domain Person Re-ID

In this article, we focus on tackling the task of unsupervised cross-domain adaptation on person re-identification (UDA re-ID). Most previous methods formulate UDA re-ID as a semi-supervised learning problem and aim to generate pseudo-labels on the target domain for training. However, the quality of pseudo-labels is far from satisfactory due to large domain gaps. To address this problem, in this work, we propose to improve the quality of pseudo-labels by handling domain shifts. Specifically, we narrow down the domain gap via domain style normalization and allow the model to behave more robustly to domain shifts by applying different perturbations on the target data. Furthermore, we point out that noises are inevitable in pseudo-labels and propose a noise-tolerant learning paradigm, which consists of positive learning on latent clean pseudo-labels and negative learning on latent noisy pseudo-labels. We conduct experiments under different adaptation scenarios, including synthetic<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\rightarrow $ </tex-math></inline-formula>real and real<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\rightarrow $ </tex-math></inline-formula>real, and demonstrate that our proposed Domain Invariant Noise-Tolerant Learning (DINTL) method achieves state-of-the-art results without additional parameters.