Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation

Abstract

It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical knowledge distillation framework to learn a lightweight pedestrian detector, which significantly reduces the computational cost and still holds the high accuracy at the same time. Following the `teacher--student' diagram that a stronger, deeper neural network can teach a lightweight network to learn better representations, we explore multiple knowledge distillation architectures and reframe this approach as a unified, hierarchical distillation framework. In particular, the proposed distillation is performed at multiple hierarchies, multiple stages in a modern detector, which empowers the student detector to learn both low-level details and high-level abstractions simultaneously. Experiment result shows that a student model trained by our framework, with 6 times compression in number of parameters, still achieves competitive performance as the teacher model on the widely used pedestrian detection benchmark.

Accepted at ICIP 2019 as Oral

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets

Cited by in corpus (6)

• From Handcrafted to Deep Features for Pedestrian Detection: A Survey
• Knowledge Distillation in Deep Learning and its Applications
• Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
• Knowledge Distillation approach towards Melanoma Detection
• Exploring the Hierarchy in Relation Labels for Scene Graph Generation
• Improved detection of small objects in road network sequences