Triplet loss with batch hard mining (TriHard loss) is an important variation of triplet loss inspired by the idea that hard triplets improve the performance of metric leaning networks. However, there is a dilemma in the training process. The hard negative samples contain various quite similar characteristics compared with anchors and positive samples in a batch. Features of these characteristics should be clustered between anchors and positive samples while are also utilized to repel between anchors and hard negative samples. It is harmful for learning mutual features within classes. Several methods to alleviate the dilemma are designed and tested. In the meanwhile, an element-weighted TriHard loss is emphatically proposed to enlarge the distance between partial elements of feature vectors selectively which represent the different characteristics between anchors and hard negative samples. Extensive evaluations are conducted on Market1501 and MSMT17 datasets and the results achieve state-of-the-art on public baselines.

We appreciate the constructive comments and valuable points raised by the reviewers and the editor. Some expressions in this paper are not proper or brief enough. We will try our best to make the writing better. It is an improvement on loss function without increasing the inference cost. Table 1 in our paper is the results of ablation study.

Summary and Contributions: This paper aims to alleviate the dilemma of triplet loss when facing hard negative samples. The "dilemma" mentioned in this paper means that the similarity between the anchor and positive sample is useful for better representation, but the similarity between the anchor and negative sample should be repelled, so processing the similarity of anchor, positive sample and hard negative samples is a dilemma problem in triplet loss. To solve this problem, an Element-weighted TriHard Loss function is designed in this paper. The main idea is to weight the feature vectors of anchor and negative sample before calculating their distance to find discriminative elements of their feature vectors. Meanwhile, three mitigation strategies of TriHard loss dilemma are discussed in this paper.

All four knowledgeable reviewers were left with a favorable opinion of this work after the author rebuttal, and the AC agrees with this positive assessment. However, during the post-rebuttal discussion phase an independent ethics review was conducted regarding the general use of the DukeMTMC dataset. Some concerns raised about use of this dataset during this ethics review include: -- "... the dataset collection involved non-consensual video surveillance of students on Duke University campus. It is unlikely that all students even knew they were being recorded, and their relative lack of power with respect to the institution surveilling them also raises concerns about the ability to meaningfully object to the surveillance." Referencing the issues and discouraging future use of the dataset would help mitigate this, as would full removal of the results."

Triplet loss with batch hard mining (TriHard loss) is an important variation of triplet loss inspired by the idea that hard triplets improve the performance of metric leaning networks. However, there is a dilemma in the training process. The hard negative samples contain various quite similar characteristics compared with anchors and positive samples in a batch. Features of these characteristics should be clustered between anchors and positive samples while are also utilized to repel between anchors and hard negative samples. It is harmful for learning mutual features within classes.