Knowledge distillation (KD) is a well-established technique for compressing neural networks
and has gained increasing attention in object detection tasks. However, typical object …

Abstract Knowledge distillation techniques have been widely used in the field of deep
learning, usually by extracting valid information from a neural network with a large number of …

Abstract Knowledge distillation (KD) has been widely used in different tasks as a practical
model compression technique. Due to the poor performance of directly using Mean Square …

The current most advanced CNN-based detection models are nearly not deployable on
mobile devices with limited arithmetic power due to problems such as too many redundant …

Recent mainstream masked distillation methods function by reconstructing selectively
masked areas of a student network from the feature map of its teacher counterpart. In these …

Abstract Knowledge distillation (KD) is a widely-used technique to train compact models in
object detection. However, there is still a lack of study on how to distill between …

Object detectors based on deep learning can run smoothly on a terminal device in complex
traffic scenes, and the model compression method has become a research hotspot …

The Algorithms of object detection are usually difficult to deploy on low-end devices due to
the large amount of computation, but knowledge distillation can solve this problem by …

Most of knowledge distillation methods for object detection are feature-based and have
achieved competitive results. However, only distillating in feature imitation part does not take …

Object detection is an important technology in the field of computer vision, but a large
number of model parameters make it difficult to deploy in embedded devices. Knowledge …