Learning Deconvolution Network for Semantic Segmentation
Preprint
Abstract
We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixel-wise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction; our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained with no external data through ensemble with the fully convolutional network.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation2015
- Convolutional feature masking for joint object and stuff segmentation2015
- Feedforward semantic segmentation with zoom-out features2015
- Hypercolumns for object segmentation and fine-grained localization2015
- Going deeper with convolutions2015
- 3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Adaptive deconvolutional networks for mid and high level feature learning2011
- Semantic contours from inverse detectors2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009