In the existing works of person re-identification (ReID), batch hard triplet loss has achieved great success. However, it only cares about the hardest samples within the batch. For any probe, there are massive mismatched samples (crucial samples) outside the batch which are closer than the matched samples. To reduce the disruptive influence of crucial samples, we propose a novel isosceles contraint for triplet. Theoretically, we show that if a matched pair has equal distance to any one of mismatched sample, the matched pair should be infinitely close. Motivated by this, the isosceles constraint is designed for the two mismatched pairs of each triplet, to restrict some matched pairs with equal distance to different mismatched samples. Meanwhile, to ensure that the distance of mismatched pairs are larger than the matched pairs, margin constraints are necessary. Minimizing the isosceles and margin constraints with respect to the feature extraction network makes the matched pairs closer and the mismatched pairs farther away than the matched ones. By this way, crucial samples are effectively reduced and the performance on ReID is improved greatly. Likewise, our isosceles contraint can be applied to quadruplet as well. Comprehensive experimental evaluations on Market-1501, DukeMTMC-reID and CUHK03 datasets demonstrate the advantages of our isosceles constraint over the related state-of-the-art approaches.

中文翻译：

---

等腰约束人重新识别。

在现有的人员重新识别（ReID）作品中，批量硬三元组丢失取得了巨大的成功。但是，它只关心批次中最硬的样品。对于任何探针，批外都有大量不匹配的样本（关键样本），比匹配的样本更接近。为了减少关键样本的破坏性影响，我们提出了一种三重态的等腰约束。从理论上讲，我们表明如果匹配对与任何一个不匹配样本的距离相等，则匹配对应无限接近。因此，等腰约束是针对每个三元组的两个不匹配对设计的，以将具有相等距离的一些匹配对限制到不同的不匹配样本。同时，为了确保不匹配对的距离大于匹配对，保证金限制是必要的。相对于特征提取网络，使等腰和边距约束最小化，使匹配对比匹配对更近，错配对比匹配对更远。通过这种方式，有效地减少了关键样本，并大大提高了ReID的性能。同样，我们的等腰约束也可以应用于四联体。对Market-1501，DukeMTMC-reID和CUHK03数据集的综合实验评估表明，等腰约束比相关的最新技术有优势。有效地减少了关键样本，并大大提高了ReID的性能。同样，我们的等腰约束也可以应用于四联体。对Market-1501，DukeMTMC-reID和CUHK03数据集的综合实验评估表明，等腰约束比相关的最新技术有优势。有效地减少了关键样本，并大大提高了ReID的性能。同样，我们的等腰约束也可以应用于四联体。对Market-1501，DukeMTMC-reID和CUHK03数据集的综合实验评估表明，等腰约束比相关的最新技术有优势。