当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
FTN: Foreground-Guided Texture-Focused Person Re-Identification
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-09-24 , DOI: arxiv-2009.11425
Donghaisheng Liu, Shoudong Han, Yang Chen, Chenfei Xia, Jun Zhao

Person re-identification (Re-ID) is a challenging task as persons are often in different backgrounds. Most recent Re-ID methods treat the foreground and background information equally for person discriminative learning, but can easily lead to potential false alarm problems when different persons are in similar backgrounds or the same person is in different backgrounds. In this paper, we propose a Foreground-Guided Texture-Focused Network (FTN) for Re-ID, which can weaken the representation of unrelated background and highlight the attributes person-related in an end-to-end manner. FTN consists of a semantic encoder (S-Enc) and a compact foreground attention module (CFA) for Re-ID task, and a texture-focused decoder (TF-Dec) for reconstruction task. Particularly, we build a foreground-guided semi-supervised learning strategy for TF-Dec because the reconstructed ground-truths are only the inputs of FTN weighted by the Gaussian mask and the attention mask generated by CFA. Moreover, a new gradient loss is introduced to encourage the network to mine the texture consistency between the inputs and the reconstructed outputs. Our FTN is computationally efficient and extensive experiments on three commonly used datasets Market1501, CUHK03 and MSMT17 demonstrate that the proposed method performs favorably against the state-of-the-art methods.

中文翻译:

FTN:前景引导纹理焦点人物重新识别

人员重新识别 (Re-ID) 是一项具有挑战性的任务,因为人员通常处于不同的背景。最新的 Re-ID 方法在人判别学习中平等对待前景和背景信息,但是当不同的人处于相似的背景或同一个人处于不同的背景时,很容易导致潜在的误报问题。在本文中,我们提出了一种用于 Re-ID 的前景引导纹理聚焦网络 (FTN),它可以弱化无关背景的表示并以端到端的方式突出与人员相关的属性。FTN 由用于 Re-ID 任务的语义编码器 (S-Enc) 和紧凑的前景注意模块 (CFA) 以及用于重建任务的纹理聚焦解码器 (TF-Dec) 组成。特别,我们为 TF-Dec 构建了一个前景引导的半监督学习策略,因为重建的地面实况只是由高斯掩码和 CFA 生成的注意力掩码加权的 FTN 输入。此外,引入了新的梯度损失以鼓励网络挖掘输入和重建输出之间的纹理一致性。我们的 FTN 在三个常用数据集 Market1501、CUHK03 和 MSMT17 上具有计算效率和广泛的实验证明,所提出的方法与最先进的方法相比表现良好。
更新日期:2020-09-25
down
wechat
bug