A Novel Optimized Context-Based Deep Architecture for Scene Parsing

No Thumbnail Available
File version
Author(s)
Mandal, R
Verma, B
Azam, B
Selvaraj, H
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
2023
Size
File type(s)
Location

Virtual event

License
Abstract

Determining the optimal parameter values for a scene parsing network architecture is an important task as a network with optimal parameters produces the best performance. A manual selection of parameter values requires expert domain knowledge of the intrinsic structure and extensive trial and error, which does not guarantee optimal results. An automatic search of the optimal parameters is desirable to harness the full potential of a scene parsing framework. The network architecture needs to be evaluated with various combinations for several parameters to achieve optimum performance. We propose a stacked three-level deep context-adaptive end-to-end network. The end-to-end network architecture extracts visual features, and contextual features, and optimally integrates both features in three logical levels for scene parsing. Particle Swarm Optimization (PSO) algorithm has been used to efficiently search for optimal solutions. Using PSO, we set an optimal set of parameters in all three levels to obtain optimum performance. The PSO aims to optimize the network globally by considering all hyperparameters in the network to achieve the best performance.

Journal Title
Conference Title

Neural Information Processing 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VI

Book Title
Edition
Volume

1793

Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject

Neural networks

Data structures and algorithms

Persistent link to this record
Citation

Mandal, R; Verma, B; Azam, B; Selvaraj, H, A Novel Optimized Context-Based Deep Architecture for Scene Parsing, Neural Information Processing 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VI, 2023, 1793, pp. 351-364