当前位置: X-MOL 学术Neural Process Lett. › 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.)
Rapid Person Re-Identification via Sub-space Consistency Regularization
Neural Processing Letters ( IF 3.1 ) Pub Date : 2022-08-23 , DOI: 10.1007/s11063-022-11002-5
Qingze Yin, Guan’an Wang, Guodong Ding, Qilei Li, Shaogang Gong, Zhenmin Tang

Person Re-Identification (ReID) matches pedestrian across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation as well as complex quick-sort algorithms. Recently, some works propose to yield binary encoded person descriptors which instead only require fast Hamming distance computation and simple counting-sort algorithms. However, the performances of such binary encoded descriptors, especially with short code (e.g, 32 and 64 bits), are hardly satisfactory given the sparse binary space. To strike a balance between the model accuracy and efficiency, we propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by 0.25 times than real-value features under same dimensions whilst maintain a competitive accuracy, especially under short codes. SCR transforms real-value features vector (e.g, 2048 float32) with short binary codes (e.g, 64 bits) by first dividing real-value features vector into M sub-spaces, each with C clustered centroids. Thus the distance between two samples can be expressed as the summation of respective distance to the centroids, which can be sped up by offline calculation and maintained via a look-up-table. On the other side, these real-value centroids help to achieve significantly higher accuracy than using binary code. Lastly, we convert the distance look-up-table to be integer and apply the counting-sort algorithm to speed up the ranking stage. We also propose a novel consistency regularization with an iterative framework. Experimental results on Market-1501 and DukeMTMC-reID show promising and exciting results. Under short code, our proposed SCR enjoys Real-value-level accuracy and Hashing-level speed.



中文翻译:

通过子空间一致性正则化快速人员重新识别

行人重新识别 (ReID) 通过不相交的摄像头匹配行人。现有的采用实值特征描述符的 ReID 方法已经达到了很高的准确率,但由于欧几里德距离计算速度慢以及快速排序算法复杂,效率低。最近,一些工作提出产生二进制编码的人描述符,而只需要快速的汉明距离计算和简单的计数排序算法。然而,这种二进制编码描述符的性能,尤其是短代码(例如, 32 和 64 位),考虑到稀疏的二进制空间,很难令人满意。为了在模型准确性和效率之间取得平衡,我们提出了一种新颖的子空间一致性正则化 (SCR) 算法,该算法可以在相同维度下将 ReID 过程加速 0.25 倍,同时保持有竞争力的准确性,尤其是在短代码。SCR通过首先将实值特征向量划分为M个子空间每个子空间包含C聚集的质心。因此,两个样本之间的距离可以表示为各自到质心的距离之和,可以通过离线计算加快速度,并通过查找表进行维护。另一方面,这些实值质心有助于实现比使用二进制代码更高的准确度。最后,我们将距离查找表转换为整数,并应用计数排序算法来加快排序阶段。我们还提出了一种具有迭代框架的新颖的一致性正则化。Market-1501 和 DukeMTMC-reID 的实验结果显示出有希望和令人兴奋的结果。在短代码下,我们提出的 SCR 具有实值级别的准确性和哈希级别的速度。

更新日期:2022-08-24
down
wechat
bug