Deep Cosine Metric Learning For Person Re-identification

Abstract

Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.

Stats

• citations303
• S2 citations—
• github stars0
• HF likes0
• heat score18.62
• arxiv keywojke2018deep

Related papers

• Cross-view Kernel Similarity Metric Learning Using Pairwise Constraints For Person Re-identification (2019)0.00
• A Semi-supervised Maximum Margin Metric Learning Approach For Small Scale Person Re-identification (2019)4.52
• Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
• Distribution Context Aware Loss For Person Re-identification (2019)3.58
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Ranking And Classification Driven Feature Learning For Person Re_identification (2019)4.01
• Large Margin Learning In Set To Set Similarity Comparison For Person Re-identification (2017)12.10
• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61