Deep Metric Learning for Practical Person Re-Identification

Abstract

Various hand-crafted features and metric learning methods prevail in the field of person re-identification. Compared to these methods, this paper proposes a more general way that can learn a similarity metric from image pixels directly. By using a "siamese" deep neural network, the proposed method can jointly learn the color feature, texture feature and metric in a unified framework. The network has a symmetry structure with two sub-networks which are connected by Cosine function. To deal with the big variations of person images, binomial deviance is used to evaluate the cost between similarities and labels, which is proved to be robust to outliers. Compared to existing researches, a more practical setting is studied in the experiments that is training and test on different datasets (cross dataset person re-identification). Both in "intra dataset" and "cross dataset" settings, the superiorities of the proposed method are illustrated on VIPeR and PRID.

Cited by in corpus (26)

• A Discriminatively Learned CNN Embedding for Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• Person Re-Identification by Camera Correlation Aware Feature Augmentation
• Learning Deep Embeddings with Histogram Loss
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques
• Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
• Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
• Embedding Deep Metric for Person Re-identication A Study Against Large Variations
• Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification
• 3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning
• Constrained Deep Metric Learning for Person Re-identification
• Survey on Deep Learning Techniques for Person Re-Identification Task
• CoLES: Contrastive Learning for Event Sequences with Self-Supervision
• Distance Metric Learning for Aspect Phrase Grouping
• Nonlinear Local Metric Learning for Person Re-identification
• Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?
• Person Recognition in Personal Photo Collections
• A heterogeneous branch and multi-level classification network for person re-identification
• It Takes Two to Tango: Mixup for Deep Metric Learning
• Incorporating Intra-Class Variance to Fine-Grained Visual Recognition
• A Simple and Effective Framework for Pairwise Deep Metric Learning
• Homocentric Hypersphere Feature Embedding for Person Re-identification
• Diversified Mutual Learning for Deep Metric Learning
• Learning adaptively from the unknown for few-example video person re-ID
• Dynamic Sampling for Deep Metric Learning