Conference paper
Reflective field for pixel-Level tasks
2018 24th International Conference on Pattern Recognition (ICPR)
24th International Conference on Pattern Recognition (ICPR) 2018 (Beijing, China, 20/08/2018–24/08/2018)
2018
Abstract
PixelNet has achieved great success in dense prediction problems with a pure pixel-level architecture, but there is still much room for improvement. In this paper, we start from PixelNet and discuss the pixel-level architecture called hypercol-umn and its limitations in building feature representation with rich semantic information. To achieve this goal, we propose a concept in the context of neural networks called reflective field, representing the area reflected by the origin input. Furthermore, the proposed reflective field is used to solve the limitations of the hypercolumn architecture. Specifically, we give the method of calculating the size of the reflective field and analyze the effective reflective field in the calculated area. Then, we use the reflective field to build a new hypercolumn architecture, which has a more rational construction. The results on PASCAL VOC segmentation dataset with our new architecture are improved.
Details
- Title
- Reflective field for pixel-Level tasks
- Authors/Creators
- L. Zhang (Author/Creator) - Xidian UniversityX. Kong (Author/Creator) - Xidian UniversityP. Shen (Author/Creator) - Xidian UniversityG. Zhu (Author/Creator) - Xidian UniversityJ. Song (Author/Creator) - Xidian UniversityS.A.A. Shah (Author/Creator) - The University of Western AustraliaM. Bennamoun (Author/Creator) - The University of Western Australia
- Publication Details
- 2018 24th International Conference on Pattern Recognition (ICPR)
- Conference
- 24th International Conference on Pattern Recognition (ICPR) 2018 (Beijing, China, 20/08/2018–24/08/2018)
- Identifiers
- 991005541709207891
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
77 Record Views