Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
This work addresses the challenge of enabling real-time 6DoF object detection on resource-constrained mobile devices for augmented and virtual reality applications, representing an incremental improvement.
The paper tackles the problem of reducing the computational complexity of 6DoF object detection networks for mobile devices, achieving a 99% reduction in memory requirements while maintaining real-time performance, though with a 50% accuracy drop in one metric.
The detection of objects considering a 6DoF pose is a common requirement to build virtual and augmented reality applications. It is usually a complex task which requires real-time processing and high precision results for adequate user experience. Recently, different deep learning techniques have been proposed to detect objects in 6DoF in RGB images. However, they rely on high complexity networks, requiring a computational power that prevents them from working on mobile devices. In this paper, we propose an approach to reduce the complexity of 6DoF detection networks while maintaining accuracy. We used Knowledge Distillation to teach portables Convolutional Neural Networks (CNN) to learn from a real-time 6DoF detection CNN. The proposed method allows real-time applications using only RGB images while decreasing the hardware requirements. We used the LINEMOD dataset to evaluate the proposed method, and the experimental results show that the proposed method reduces the memory requirement by almost 99\% in comparison to the original architecture with the cost of reducing half the accuracy in one of the metrics. Code is available at https://github.com/heitorcfelix/singleshot6Dpose.