Back to Search
Start Over
Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
- Source :
- IJCNN
- Publication Year :
- 2020
-
Abstract
- 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.<br />This paper was accepted by 2020 International Joint Conference on Neural Networks (IJCNN)
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
business.industry
Computer Vision and Pattern Recognition (cs.CV)
Deep learning
Image and Video Processing (eess.IV)
Computer Science - Computer Vision and Pattern Recognition
68-04
020207 software engineering
02 engineering and technology
Electrical Engineering and Systems Science - Image and Video Processing
Convolutional neural network
Object detection
Machine Learning (cs.LG)
Computer engineering
FOS: Electrical engineering, electronic engineering, information engineering
0202 electrical engineering, electronic engineering, information engineering
Code (cryptography)
RGB color model
020201 artificial intelligence & image processing
Augmented reality
Artificial intelligence
business
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- IJCNN
- Accession number :
- edsair.doi.dedup.....930fd6b4761fa2ccaf20472c9cbcdb75