RGB-Infrared person re-identification (RGB-IR Re- ID) is a cross-modality
matching problem, where the modality discrepancy is a big challenge. Most
existing works use Euclidean metric based constraints to resolve the
discrepancy between features of images from different modalities. However,
these methods are incapable of learning angularly discriminative feature
embedding because Euclidean distance cannot measure the included angle between
embedding vectors effectively. As an angularly discriminative feature space is
important for classifying the human images based on their embedding vectors, in
this paper, we propose a novel ranking loss function, named Bi-directional
Exponential Angular Triplet Loss, to help learn an angularly separable common
feature space by explicitly constraining the included angles between embedding
vectors. Moreover, to help stabilize and learn the magnitudes of embedding
vectors, we adopt a common space batch normalization layer. The quantitative
and qualitative experiments on the SYSU-MM01 and RegDB dataset support our
analysis. On SYSU-MM01 dataset, the performance is improved from 7.40% / 11.46%
to 38.57% / 38.61% for rank-1 accuracy / mAP compared with the baseline. The
proposed method can be generalized to the task of single-modality Re-ID and
improves the rank-1 accuracy / mAP from 92.0% / 81.7% to 94.7% / 86.6% on the
Market-1501 dataset, from 82.6% / 70.6% to 87.6% / 77.1% on the DukeMTMC-reID
dataset. Code: this https URL

本文提出了一种新颖的排名损失函数 Bi-directional Exponential Angular Triplet Loss，并采用常规空间批量归一化层来帮助稳定和学习嵌入向量的大小，以帮助学习一个角度可分的共同特征空间。在 SYSU-MM01 和 RegDB 数据集上进行的定量和定性实验证明了我们分析的有效性。