This ARC Discovery Project aims to develop a novel deep learning network architecture with contextual adaptive features for image parsing that can improve the object detection accuracy in real-world applications. A number of innovative methods for deep learning, contextual features and network parameter selection will be developed and investigated. The impact of the proposed architecture and features will be improved object-detection accuracy and advances in deep learning network architecture for image parsing. The intended outcomes are deep learning network architecture, contextual feature extraction techniques and network parameter optimisation techniques for image parsing. 

The code and data being developed for Image Parsing architecture are available on GitHub. You can download code & data from the links give nbelow. It is highly recommended to run the code using different data including custom datasets and let us know any new results you get. 

You can download the code, models, and data to run the demo and obtain results at the following link : Demo

This research project has produced numerous journal and conference papers so far. 

• B. Azam, R. Mandal, and B. Verma. Relationship Aware Context Adaptive Framework for Image Parsing.  in Information Sciences vol. 607, pp. 506-518, 2022. [PDF] [Available Online] [Code]

• B. Azam, B. Verma, and M. Zhang, "Context-Adaptive Deep Learning for Efficient Image Parsing in Remote Sensing: An Automated Parameter Selection Approach"  2023 IEEE Symposium Series on Computational Intelligence (SSCI)  Mexico City, Mexico, pp. 258-263  [PDF] [Available Online] [Code]

• R. Mandal, and B. Verma, "Parameter Optimisation for Context-Adaptive Deep Layered Network for Semantic Segmentation"  2023 IEEE Symposium Series on Computational Intelligence (SSCI)  Mexico City, Mexico, pp. 258-263 [PDF] [Avalilable Online] 

• B. Azam, and B. Verma. “A Graph-based Context Learning Technique for Image Parsing” 2023 Internation Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, 2023, pp. 1-10 [PDF] [Available Online] [Code].

• R. Mandal, B. Azam, B. Verma, and M. Zhang. “Genetic Algorithms for Optimising Context-based Neural Networks for Image Segmentation” IEEE Symposium Series on Computational Intelligence (SSCI), 2022 pp. 01-08  [PDF] [Available Online] .

• R. Mandal, B. Verma, B. Azam, and H. Selvaraj" A Novel Optimised Context-Based Deep Architecture for Scene Parsing,"  International Conference on Neural Information Processing (ICONIP), 2022 pp. 01-08 [PDF] [Available Online] .

• B. Azam, R. Mandal and B. Verma. Fully Convolutional Neural Network with Relation Aware Context Information for Image Parsing, 2021 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2021, pp. 01-06. [PDF] [Available Online] [Code]

• R. Mandal, B. Azam and B. Verma. Context-based Deep Learning Architecture with Optimal Integration Layer for Image Parsing, International Conference on Neural Information Processing (ICONIP), 2021, pp. 285-296. [PDF] [Available Online] [Code]

• B. Azam, R. Mandal, and B. Verma, "Relationship Aware Context Adaptive Feature Selection Framework for Image Parsing," 2021 International Joint Conference on Neural Networks (IJCNN) 2021, pp. 1-7  [PDF] [Available Online] [Code]

• R. Mandal, B. Azam B. Verma, and M. Zhang. Deep Learning Model with GA-based Visual Feature Selection and Context Integration, in 2021 IEEE Congress on Evolutionary Computation (CEC)  2021, pp. 288-295 [PDF] [Available Online] [Code] 

• B. Azam, R. Mandal, L. Zhang, and B. Verma, "Class Probability-based Visual and Contextual Feature Integration for Image Parsing," 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), 2020, pp. 1-6   [PDF]  [Available Online] [Code]

Presentations

• IJCNN- 2023: A Graph-based Context Learning Technique for Image Parsing.  [Slides]  

• SET - RHD - Seminar 2021:  Image Parsing.  [Slides]  

• SSCI- 2022: Genetic Algorithms for Optimising Context-based Neural Networks for Image Segmentation.  [Slides]  

• ICONIP - 2022: A Novel Optimised Context-Based Deep Architecture for Scene Parsing.  [Slides]  

• DICTA - 2021: Fully Convolutional Neural Network with Relation Aware Context Information for Image Parsing.  [Slides]  

• ICONIP - 2021:  Context-based Deep Learning Architecture with Optimal Integration Layer for Image Parsing.  [Slides]  

• IJCNN - 2021: Relationship Aware Context Adaptive Feature Selection Framework for Image Parsing.  [Slides]  

• CEC - 2021: Deep Learning Model with GA-based Visual Feature Selection and Context Integration.  [Slides]  

• IVCNZ - 2020: Class Probability-based Visual and Contextual Feature Integration for Image Parsing.   [Slides]