File(s) not publicly available
Class probability-based visual and contextual feature integration for image parsing
conference contribution
posted on 2021-06-25, 01:01 authored by Basim Azam, Ranju Mandal, Ligang ZhangLigang Zhang, Brijesh VermaDeep learning networks have become one of the most promising architectures for image parsing tasks. Although existing deep networks consider global and local contextual information of the images to learn coarse features individually, they lack automatic adaptation to the contextual properties of scenes. In this work, we present a visual and contextual feature-based deep network for image parsing. The main novelty is in the 3-layer architecture which considers contextual information and each layer is independently trained and integrated. The network explores the contextual features along with the visual features for class label prediction with class-specific classifiers. The contextual features consider the prior information learned by calculating the co-occurrence of object labels both within a whole scene and between neighboring superpixels. The class-specific classifier deals with an imbalance of data for various object categories and learns the coarse features for every category individually. A series of weak classifiers in combination with boosting algorithms are investigated as classifiers along with the aggregated contextual features. The experiments were conducted on the benchmark Stanford background dataset which showed that the proposed architecture produced the highest average accuracy and comparable global accuracy.
Funding
Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)
History
Volume
2020-NovemberStart Page
1End Page
6Number of Pages
6Start Date
2021-11-25Finish Date
2021-11-27eISSN
2151-2205ISSN
2151-2191ISBN-13
9781728185798Location
Wellington, New ZealandPublisher
IEEEPlace of Publication
Piscataway, NJPublisher DOI
Full Text URL
Peer Reviewed
- Yes
Open Access
- No
Author Research Institute
- Centre for Intelligent Systems
Era Eligible
- Yes