Learning affordance segmentation: An investigative study
Abstract
Affordance segmentation aims at recognising, localising and segmenting affordances from images, enabling scene understanding of visual content in many applications in robotic perception. Supervised learning with deep networks has become very popular in affordance segmentation. However, very few studies have investigated the factors that contribute to improved learning of affordances. This investigation is essential to improve precision and balance cost-efficiency when learning affordance segmentation. In this paper, we address this task and identify two prime factors affecting precision of learning affordance segmentation: (1) The quality of features extracted from the classification module and (2) the dearth of information in the Region Proposal Network (RPN). Consequently, we replace the backbone classification model and introduce a novel multiple alignment strategy in the RPN. Our results obtained through extensive experimentation validate our contributions and outperform the state-of-the-art affordance segmentation models.
RAS ID
35490
Document Type
Conference Proceeding
Date of Publication
2020
Funding Information
Edith Cowan University
School
School of Science
Copyright
subscription content
Publisher
IEEE
Recommended Citation
Minh, C., Gilani, S., Islam, S. M., & Suter, D. (2020). Learning affordance segmentation: An investigative study. DOI: https://doi.org/10.1109/DICTA51227.2020.9363390
Comments
Minh, C. N. D., Gilani, S. Z., Islam, S. M. S., & Suter, D. (2020, November - December). Learning affordance segmentation: An investigative study [Paper Presentation]. 2020 Digital Image Computing: Techniques and Applications, (DICTA), Melbourne, Australia. https://doi.org/10.1109/DICTA51227.2020.9363390