Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification

TLDR

Person re‑identification is a key task in wide‑area video surveillance, and deep learning models with triplet loss are commonly used, but triplet loss focuses mainly on ordering and suffers from weak generalization, leading to inferior performance. This work proposes a quadruplet loss to increase inter‑class variation and reduce intra‑class variation, aiming to improve generalization. The authors implement a quadruplet deep network that employs margin‑based online hard negative mining to train the model under the quadruplet loss. The resulting network demonstrates superior generalization and outperforms most state‑of‑the‑art methods on representative person ReID datasets.

Abstract

Person re-identification (ReID) is an important task in wide area video surveillance which focuses on identifying people across different cameras. Recently, deep learning networks with a triplet loss become a common framework for person ReID. However, the triplet loss pays main attentions on obtaining correct orders on the training set. It still suffers from a weaker generalization capability from the training set to the testing set, thus resulting in inferior performance. In this paper, we design a quadruplet loss, which can lead to the model output with a larger inter-class variation and a smaller intra-class variation compared to the triplet loss. As a result, our model has a better generalization ability and can achieve a higher performance on the testing set. In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID. In extensive experiments, the proposed network outperforms most of the state-of-the-art algorithms on representative datasets which clearly demonstrates the effectiveness of our proposed method.