A Discriminatively Learned CNN Embedding For Person Re-identification

Abstract

We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a new siamese network that simultaneously computes identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus making full usage of the annotations. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied in image retrieval.

Stats

• citations511
• S2 citations—
• github stars0
• HF likes0
• heat score20.32
• arxiv keyzheng2016a

Related papers

• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71
• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Ranking And Classification Driven Feature Learning For Person Re_identification (2019)4.01
• Ensemble Feature For Person Re-identification (2019)0.00