Back to Search
Start Over
Small Network for Lightweight Task in Computer Vision: A Pruning Method Based on Feature Representation
- Source :
- Computational Intelligence and Neuroscience, Vol 2021 (2021), Computational Intelligence and Neuroscience
- Publication Year :
- 2021
- Publisher :
- Hindawi, 2021.
-
Abstract
- Many current convolutional neural networks are hard to meet the practical application requirement because of the enormous network parameters. For accelerating the inference speed of networks, more and more attention has been paid to network compression. Network pruning is one of the most efficient and simplest ways to compress and speed up the networks. In this paper, a pruning algorithm for the lightweight task is proposed, and a pruning strategy based on feature representation is investigated. Different from other pruning approaches, the proposed strategy is guided by the practical task and eliminates the irrelevant filters in the network. After pruning, the network is compacted to a smaller size and is easy to recover accuracy with fine-tuning. The performance of the proposed pruning algorithm is validated on the acknowledged image datasets, and the experimental results prove that the proposed algorithm is more suitable to prune the irrelevant filters for the fine-tuning dataset.
- Subjects :
- Speedup
General Computer Science
Article Subject
Computer science
General Mathematics
Computer applications to medicine. Medical informatics
R858-859.7
Inference
Neurosciences. Biological psychiatry. Neuropsychiatry
02 engineering and technology
Machine learning
computer.software_genre
Convolutional neural network
Image (mathematics)
Task (project management)
0202 electrical engineering, electronic engineering, information engineering
Pruning (decision trees)
Representation (mathematics)
Computers
business.industry
General Neuroscience
General Medicine
Data Compression
020202 computer hardware & architecture
Feature (computer vision)
020201 artificial intelligence & image processing
Neural Networks, Computer
Artificial intelligence
business
computer
Algorithms
Research Article
RC321-571
Subjects
Details
- Language :
- English
- ISSN :
- 16875265
- Database :
- OpenAIRE
- Journal :
- Computational Intelligence and Neuroscience
- Accession number :
- edsair.doi.dedup.....369214c534955baf2565d09ef91c2ec5
- Full Text :
- https://doi.org/10.1155/2021/5531023