Improving Fully Convolution Network for Semantic Segmentation
arXiv:1611.08986
Abstract
Fully Convolution Networks (FCN) have achieved great success in dense prediction tasks including semantic segmentation. In this paper, we start from discussing FCN by understanding its architecture limitations in building a strong segmentation network. Next, we present our Improved Fully Convolution Network (IFCN). In contrast to FCN, IFCN introduces a context network that progressively expands the receptive fields of feature maps. In addition, dense skip connections are added so that the context network can be effectively optimized. More importantly, these dense skip connections enable IFCN to fuse rich-scale context to make reliable predictions. Empirically, those architecture modifications are proven to be significant to enhance the segmentation performance. Without engaging any contextual post-processing, IFCN significantly advances the state-of-the-arts on ADE20K (ImageNet scene parsing), Pascal Context, Pascal VOC 2012 and SUN-RGBD segmentation datasets.
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Residual Learning for Image Recognition
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- ParseNet: Looking Wider to See Better
- Fully Convolutional Networks for Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- Simultaneous Detection and Segmentation
- Semantic Understanding of Scenes through the ADE20K Dataset
- Semantic Image Segmentation via Deep Parsing Network
- Bridging Category-level and Instance-level Semantic Image Segmentation
- PixelNet: Towards a General Pixel-level Architecture
- Feedforward semantic segmentation with zoom-out features
- DAG-Recurrent Neural Networks For Scene Labeling
- Top-Down Learning for Structured Labeling with Convolutional Pseudoprior