Bi-Directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

Abstract

RGB-Infrared person re-identification (RGB-IR Re-ID) is a cross-modality matching problem with promising applications in the dark environment. Most existing works use Euclidean metric based constraints to resolve the discrepancy between features of 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. Quantitative 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.

Towards a Unified Middle Modality Learning for Visible-Infrared Person Re-Identification

“…We first compare the proposed MMN method with several other state-of-the-art methods to demonstrate the superiority of MMN method. The competing methods include the methods based on feature extraction (including Zero-Padding [40], HCML [44], MHM [41], BDTR [46], MAC [43], cmGAN [3], MSR [7], HSME [12], SNR [16], expAT [42], CMM [22], CMSP [39], SSFT [24], DDAA [45], CoAL [38], NFS [1]) and the methods based on image generation (including D 2 RL [36], JSIA-ReID [35], AlignGAN [34], Hi-CMD [2], DG-VAE [29], X-Modality [20]). The results on the RegDB and SYSU-MM01 datasets are reported in Table 1.…”

Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting

“…Zhang et al mitigated the modality discrepancy by mapping the heterogeneous representations into a common space [42]. To learn an angularly separable common feature space, Ye et al [1] constrained the angles between feature vectors. Cai et al [43] proposed a dual-modality hard mining triplet-center loss (DTCL) which can reduce computational cost and mine hard triplet samples.…”

“…Person re-identification (ReID) is a fundamental building block in various tasks of computer vision, such as intelligent surveillance, video analysis [1], and criminal investigation [2]. With the advancement of intelligent monitoring and the enormous expansion of video data in recent years, conventional human power has been challenging and insufficient to deal with intricate surveillance scenarios.…”

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

“…Influence of CMCC Loss: As shown in Table 3, the model with CMCC loss (B+CMCC) achieves a rank-1 accuracy of 56.63% and an mAP of 54.93%, which are higher than the baseline (B) by 7.47% and 7.95%, respectively. Besides, we implement expAT loss [40] and triplet center loss (TC) [12] with the baseline respectively. Compared with B+expAT and B+TC, the addition of CMCC loss brings a marked performance boost to baseline.…”