Learning a Discriminative Null Space for Person Re-identification

Abstract

Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views. Typically a person's appearance is represented using features of thousands of dimensions, whilst only hundreds of training samples are available due to the difficulties in collecting matched training images. With the number of training samples much smaller than the feature dimension, the existing methods thus face the classic small sample size (SSS) problem and have to resort to dimensionality reduction techniques and/or matrix regularisation, which lead to loss of discriminative power. In this work, we propose to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data. In this null space, images of the same person are collapsed into a single point thus minimising the within-class scatter to the extreme and maximising the relative between-class separation simultaneously. Importantly, it has a fixed dimension, a closed-form solution and is very efficient to compute. Extensive experiments carried out on five person re-identification benchmarks including VIPeR, PRID2011, CUHK01, CUHK03 and Market1501 show that such a simple approach beats the state-of-the-art alternatives, often by a big margin.

arXiv commentaccepted by CVPR2016

Cited by in corpus (13)

• A Discriminatively Learned CNN Embedding for Person Re-identification
• On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• Cross-Resolution Learning for Face Recognition
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• Learning to Disentangle Scenes for Person Re-identification
• Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
• CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
• Neural Person Search Machines
• Cross Domain Knowledge Transfer for Person Re-identification
• A framework with updateable joint images re-ranking for Person Re-identification
• Metric Learning in Codebook Generation of Bag-of-Words for Person Re-identification