Deep Cosine Metric Learning for Person Re-Identification
Preprint
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.Keywords
All Related Versions
- Version 1, 2018-12-02, ArXiv
- Published version: , 748.
This publication has 25 references indexed in Scilit:
- Identity Mappings in Deep Residual Networks2016
- Gated Siamese Convolutional Neural Network Architecture for Human Re-identification2016
- A Siamese Long Short-Term Memory Architecture for Human Re-identification2016
- A Discriminative Feature Learning Approach for Deep Face Recognition2016
- FaceNet: A unified embedding for face recognition and clustering2015
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identification2014
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Microsoft COCO: Common Objects in Context2014
- Large scale metric learning from equivalence constraints2012
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005