Person re-identification (re-ID) is the task of matching the same individuals across multiple cameras, and its performance is greatly influenced by background clutter. Most re-ID methods remove background clutter using hard manners, such as the use of segmentation algorithms. However, the hard manner may damage the structure information and smoothness of original images. In this work, we propose a unidirectional information-interaction network (UI2N) that consists of a global stream (G-Stream) and a background-graying stream (BGg-Stream). The G-Stream and BGg-Stream carry out unidirectional information interaction such that their features are complementary. We further propose a soft manner with the UI2N to weaken background clutter by background-graying. The soft manner can help the UI2N filter out background interference and retain some informative background cues. Extensive evaluations demonstrate that our method significantly outperforms many state-of-the-art approaches in the challenging Market-1501, DukeMTMC-reID, and CUHK03-NP datasets.

中文翻译：

---

用于行人重识别的单向信息交互网络

行人重识别（re-ID）是跨多个摄像头匹配同一个人的任务，其性能受背景杂波影响很大。大多数 re-ID 方法使用硬方式去除背景杂波，例如使用分割算法。然而，硬方式可能会破坏原始图像的结构信息和平滑度。在这项工作中，我们提出了一个由全局流（G-Stream）和背景灰度流（BGg-Stream）组成的单向信息交互网络（UI2N）。G-Stream和BGg-Stream进行单向信息交互，特性互补。我们进一步提出了一种使用 UI2N 的软方式，通过背景灰度来减弱背景杂波。柔和的方式可以帮助 UI2N 过滤掉背景干扰并保留一些信息丰富的背景线索。广泛的评估表明，我们的方法在具有挑战性的 Market-1501、DukeMTMC-reID 和 CUHK03-NP 数据集中明显优于许多最先进的方法。