Stacked Deconvolutional Network for Semantic Segmentation

2017/08/16 by Jun Fu, Jing Liu, Fu, Jun +5 · 3 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.1708.04943

openalex publication_date 2017/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent progress in semantic segmentation has been driven by improving the spatial resolution under Fully Convolutional Networks (FCNs). To address this problem, we propose a Stacked Deconvolutional Network (SDN) for semantic segmentation. In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information. Meanwhile, inter-unit and intra-unit connections are designed to assist network training and enhance feature fusion since the connections improve the flow of information and gradient propagation throughout the network. Besides, hierarchical supervision is applied during the upsampling process of each SDN unit, which guarantees the discrimination of feature representations and benefits the network optimization. We carry out comprehensive experiments and achieve the new state-of-the-art results on three datasets, including PASCAL VOC 2012, CamVid, GATECH. In particular, our best model without CRF post-processing achieves an intersection-over-union score of 86.6% in the test set.

Citations

• The Pascal Visual Object Classes (VOC) Challenge
• Semantic Image Segmentation via Deep Parsing Network
• Gradient-based learning applied to document recognition
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet classification with deep convolutional neural networks
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deformable Convolutional Networks
• Stacked Hourglass Networks for Human Pose Estimation
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Learning Deconvolution Network for Semantic Segmentation

Cited by

• Microscopic image processing platform for multi-class cell segmentation using deep learning
• Affinity Derivation and Graph Merge for Instance Segmentation
• Dual Attention Network for Scene Segmentation

Related

• Learning Deconvolution Network for Semantic Segmentation
• Fully Convolutional Networks for Semantic Segmentation
• Fully Convolutional Networks for Semantic Segmentation
• EfficientFCN: Holistically-guided Decoding for Semantic Segmentation
• Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation