Recursive Neural Networks Based on PSO for Image Parsing
This paper presents an image parsing algorithm which is based on Particle Swarm Optimization (PSO) and Recursive Neural Networks (RNNs). State-of-the-art method such as traditional RNN-based parsing strategy uses L-BFGS over the complete data for learning the parameters. However, this could cause pr...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | Abstract and Applied Analysis |
| Online Access: | http://dx.doi.org/10.1155/2013/617618 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832561758994169856 |
|---|---|
| author | Guo-Rong Cai Shui-Li Chen |
| author_facet | Guo-Rong Cai Shui-Li Chen |
| author_sort | Guo-Rong Cai |
| collection | DOAJ |
| description | This paper presents an image parsing algorithm which is based on Particle Swarm Optimization (PSO) and Recursive Neural Networks (RNNs). State-of-the-art method such as traditional RNN-based parsing strategy uses L-BFGS over the complete data for learning the parameters. However, this could cause problems due to the nondifferentiable objective function. In order to solve this problem, the PSO algorithm has been employed to tune the weights of RNN for minimizing the objective. Experimental results obtained on the Stanford background dataset show that our PSO-based training algorithm outperforms traditional RNN, Pixel CRF, region-based energy, simultaneous MRF, and superpixel MRF. |
| format | Article |
| id | doaj-art-3583aed06ae6488cb7433c8ff48bc474 |
| institution | Kabale University |
| issn | 1085-3375 1687-0409 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Abstract and Applied Analysis |
| spelling | doaj-art-3583aed06ae6488cb7433c8ff48bc4742025-02-03T01:24:13ZengWileyAbstract and Applied Analysis1085-33751687-04092013-01-01201310.1155/2013/617618617618Recursive Neural Networks Based on PSO for Image ParsingGuo-Rong Cai0Shui-Li Chen1School of Sciences, Jimei University, Xiamen, ChinaSchool of Sciences, Jimei University, Xiamen, ChinaThis paper presents an image parsing algorithm which is based on Particle Swarm Optimization (PSO) and Recursive Neural Networks (RNNs). State-of-the-art method such as traditional RNN-based parsing strategy uses L-BFGS over the complete data for learning the parameters. However, this could cause problems due to the nondifferentiable objective function. In order to solve this problem, the PSO algorithm has been employed to tune the weights of RNN for minimizing the objective. Experimental results obtained on the Stanford background dataset show that our PSO-based training algorithm outperforms traditional RNN, Pixel CRF, region-based energy, simultaneous MRF, and superpixel MRF.http://dx.doi.org/10.1155/2013/617618 |
| spellingShingle | Guo-Rong Cai Shui-Li Chen Recursive Neural Networks Based on PSO for Image Parsing Abstract and Applied Analysis |
| title | Recursive Neural Networks Based on PSO for Image Parsing |
| title_full | Recursive Neural Networks Based on PSO for Image Parsing |
| title_fullStr | Recursive Neural Networks Based on PSO for Image Parsing |
| title_full_unstemmed | Recursive Neural Networks Based on PSO for Image Parsing |
| title_short | Recursive Neural Networks Based on PSO for Image Parsing |
| title_sort | recursive neural networks based on pso for image parsing |
| url | http://dx.doi.org/10.1155/2013/617618 |
| work_keys_str_mv | AT guorongcai recursiveneuralnetworksbasedonpsoforimageparsing AT shuilichen recursiveneuralnetworksbasedonpsoforimageparsing |