PT Journal
AU Idoia Ruiz
   Bogdan Raducanu
   Rakesh Mehta
   Jaume Amores
TI Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation
SO Engineering Applications of Artificial Intelligence
JI EAAI
PY 2020
BP 103309
VL 87
DE Person re-identification; Network distillation; Image retrieval; Model compression; Surveillance
AB 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.
ER