Analysis of Efficient CNN Design Techniques for Semantic Segmentation
| Autor: | Senthil Yogamani, Alexandre Briot, Prashanth Viswanath |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Hardware architecture
Computer science business.industry 02 engineering and technology Benchmarking 010501 environmental sciences Semantics 01 natural sciences Network planning and design Reduction (complexity) Computer engineering Software deployment Margin (machine learning) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | CVPR Workshops |
| DOI: | 10.1109/cvprw.2018.00109 |
| Popis: | Majority of CNN architecture design is aimed at achieving high accuracy in public benchmarks by increasing the complexity. Typically, they are over-specified by a large margin and can be optimized by a factor of 10-100x with only a small reduction in accuracy. In spite of the increase in computational power of embedded systems, these networks are still not suitable for embedded deployment. There is a large need to optimize for hardware and reduce the size of the network by orders of magnitude for computer vision applications. This has led to a growing community which is focused on designing efficient networks. However, CNN architectures are evolving rapidly and efficient architectures seem to lag behind. There is also a gap in understanding the hardware architecture details and incorporating it into the network design. The motivation of this paper is to systematically summarize efficient design techniques and provide guidelines for an application developer. We also perform a case study by benchmarking various semantic segmentation algorithms for autonomous driving. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|