Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
This work addresses the need for efficient pedestrian detection in real-world applications, representing an incremental improvement through a novel distillation method.
The paper tackles the challenge of building a pedestrian detection system that balances accuracy and speed by introducing a hierarchical knowledge distillation framework, which reduces computational cost by 6 times in parameters while maintaining competitive performance on a benchmark.
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.