Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions
Paper in proceeding, 2019

Semantic segmentation and instance level segmentation made substantial progress in recent years due to the emergence of deep neural networks (DNNs). A number of deep architectures with Convolution Neural Networks (CNNs) were proposed that surpass the traditional machine learning approaches for segmentation by a large margin. These architectures predict the directly observable semantic category of each pixel by usually optimizing a cross-entropy loss. In this work we push the limit of semantic segmentation towards predicting semantic labels of directly visible as well as occluded objects or objects parts, where the network's input is a single depth image. We group the semantic categories into one background and multiple foreground object groups, and we propose a modification of the standard cross-entropy loss to cope with the settings. In our experiments we demonstrate that a CNN trained by minimizing the proposed loss is able to predict semantic categories for visible and occluded object parts without requiring to increase the network size (compared to a standard segmentation task). The results are validated on a newly generated dataset (augmented from SUNCG) dataset.

Author

Pulak Purkait

University of Adelaide

Christopher Zach

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Ian Reid

University of Adelaide

IEEE International Conference on Intelligent Robots and Systems

21530858 (ISSN) 21530866 (eISSN)

1998-2005
978-1-7281-4004-9 (ISBN)

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Macau, China,

Subject Categories

Bioinformatics (Computational Biology)

Computer Science

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/IROS40897.2019.8967582

More information

Latest update

4/21/2023