Triplet Ratio Loss for Robust Person Re-identification

Triplet loss has been proven to be useful in the task of person re-identification (ReID). However, it has limitations due to the influence of large intra-pair variations and unreasonable gradients. In this paper, we propose a novel loss to reduce the influence of large intra-pair variations and improve optimization gradients via optimizing the ratio of intra-identity distance to inter-identity distance. As it also requires a triplet of pedestrian images, we call this new loss as triplet ratio loss. Experimental results on four widely used ReID benchmarks, i.e., Market-1501, DukeMTMC-ReID, CUHK03, and MSMT17, demonstrate that the triplet ratio loss outperforms the previous triplet loss.