Toward Achieving Robust Low-Level and High-Level Scene Parsing
- 31 October 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 28 (3) , 1378-1390
Abstract
In this paper, we address the challenging task of scene segmentation. We first discuss and compare two widely used approaches to retain detailed spatial information from pre-trained convolutional context network (CNN)-"dilation" and "skip". Then, we demonstrate that the parsing performance of "skip" network can be noticeably improved by modifying the parameterization of skip layers. Furthermore, we introduce a "dense skip" architecture to retain a rich set of low-level information from the pre-trained CNN, which is essential to improve the low-level parsing performance. Meanwhile, we propose a CCN and place it on top of pre-trained CNNs, which is used to aggregate contexts for high-level feature maps so that robust high-level parsing can be achieved. We name our segmentation network enhanced fully convolutional network (EFCN) based on its significantly enhanced structure over FCN. Extensive experimental studies justify each contribution separately. Without bells and whistles, EFCN achieves state-of-the-arts on segmentation datasets of ADE20K, Pascal Context, SUN-RGBD, and Pascal VOC 2012.Keywords
This publication has 23 references indexed in Scilit:
- Learning Deconvolution Network for Semantic Segmentation2015
- Feedforward semantic segmentation with zoom-out features2015
- Hypercolumns for object segmentation and fine-grained localization2015
- SUN RGB-D: A RGB-D scene understanding benchmark suite2015
- Fully convolutional networks for semantic segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- The Role of Context for Object Detection and Semantic Segmentation in the Wild2014
- SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels2013
- A Category-Level 3D Object Dataset: Putting the Kinect to Work2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009