Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation

Abstract

Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between accuracy and speed. We analyse this trade-off, comparing a classical method, that comprises hand-crafted feature description and metric learning, in particular, LOMO and XQDA, to deep learning based techniques, using image classification networks, ResNet and MobileNets. Additionally, we propose and analyse network distillation as a learning strategy to reduce the computational cost of the deep learning approach at test time. We evaluate both methods on the Market-1501 and DukeMTMC-reID large-scale datasets, showing that distillation helps reducing the computational cost at inference time while even increasing the accuracy performance.

arXiv commentPublished on the journal "Engineering Applications of Artificial Intelligence"

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• FitNets: Hints for Thin Deep Nets
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Do Deep Nets Really Need to be Deep?
• Person Re-identification: Past, Present and Future
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
• Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification