CVApr 6, 2017

Beyond triplet loss: a deep quadruplet network for person re-identification

arXiv:1704.01719v11206 citations
Originality Incremental advance
AI Analysis

This work addresses a domain-specific problem in video surveillance for person re-identification, offering an incremental improvement over existing triplet loss methods.

The paper tackles the problem of person re-identification by proposing a quadruplet loss to improve generalization from training to testing sets, resulting in higher performance that outperforms most state-of-the-art algorithms on representative datasets.

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.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes