当前位置: X-MOL 学术Cognit. Comput. › 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.)
3W-AlignNet: a Feature Alignment Framework for Person Search with Three-Way Decision Theory
Cognitive Computation ( IF 4.3 ) Pub Date : 2021-07-06 , DOI: 10.1007/s12559-021-09898-7
Yuting Yang 1 , Duoqian Miao 1 , Hongyun Zhang 2
Affiliation  

Person search aims to locate and recognize a specified person from a gallery of uncropped scene images, which combines pedestrian detection and person re-identification (re-ID). Existing methods based on Faster R-CNN have been widely used to tackle the two sub-tasks jointly, but they ignore the feature misalignment problem, i.e., re-ID feature localization is not fully aligned with the detected bounding boxes (BBoxes). Due to the fine-grained property of re-ID, it is crucial to extract accurate appearance features. In addition, the granularity of BBoxes detected from gallery images is quite different, and it is defective to treat gallery boxes with different granularity as equal in estimating their similarities with the query. Three-way decision methods are fields of research on human-inspired computation. Inspired by them, we propose a three-way-based feature alignment framework (3W-AlignNet) to optimize the re-ID feature localization. The framework is implemented by iteratively generating new BBoxes and features from previous BBoxes. The three-way decision theory is applied to avoid the mismatch problem caused by increasing Intersection over Union (IoU). We further propose a Granularity Weighted Similarity (GWS) algorithm to relieve the granularity mismatch problem. Extensive experiments show that our method outperforms all other state-of-the-art end-to-end methods on two widely used person search datasets, CUHK-SYSU and PRW.



中文翻译:

3W-AlignNet:基于三向决策理论的人物搜索特征对齐框架

人物搜索旨在从未裁剪的场景图像库中定位和识别指定的人物,它结合了行人检测和人物重新识别 (re-ID)。现有的基于 Faster R-CNN 的方法已被广泛用于联合处理这两个子任务,但它们忽略了特征错位问题,即 re-ID 特征定位与检测到的边界框 (BBoxes) 不完全对齐。由于 re-ID 的细粒度特性,提取准确的外观特征至关重要。此外,从图库图像中检测到的 BBox 的粒度差异很大,在估计它们与查询的相似性时,将不同粒度的图库框视为相等是有缺陷的。三向决策方法是人类启发计算的研究领域。受到他们的启发,我们提出了一个基于三向的特征对齐框架(3W-AlignNet)来优化 re-ID 特征定位。该框架是通过从以前的 BBox 迭代生成新 BBox 和功能来实现的。应用三路决策理论来避免因增加联合交集(IoU)而导致的不匹配问题。我们进一步提出了一种粒度加权相似性(GWS)算法来缓解粒度不匹配问题。大量实验表明,我们的方法在两个广泛使用的人物搜索数据集 CUHK-SYSU 和 PRW 上优于所有其他最先进的端到端方法。应用三路决策理论来避免因增加联合交集(IoU)而导致的不匹配问题。我们进一步提出了一种粒度加权相似性(GWS)算法来缓解粒度不匹配问题。大量实验表明,我们的方法在两个广泛使用的人物搜索数据集 CUHK-SYSU 和 PRW 上优于所有其他最先进的端到端方法。应用三路决策理论来避免因增加联合交集(IoU)而导致的不匹配问题。我们进一步提出了一种粒度加权相似性(GWS)算法来缓解粒度不匹配问题。大量实验表明,我们的方法在两个广泛使用的人物搜索数据集 CUHK-SYSU 和 PRW 上优于所有其他最先进的端到端方法。

更新日期:2021-07-06
down
wechat
bug