Label Refinement Network for Coarse-to-Fine Semantic Segmentation

2017/03/01 by Amirul Islam, Md Amirul Islam, Shujon Naha +9 · 5 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Medical Image Segmentation Techniques #cs.CV

paper · pdf · doi:10.48550/arxiv.1703.00551

9 pages

arxiv created 2017/03/01 · openalex publication_date 2017/03/01 · arxiv updated 2017/03/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions. The segmentation labels at a coarse resolution are used together with convolutional features to obtain finer resolution segmentation labels. We define loss functions at several stages in the network to provide supervisions at different stages. Our experimental results on several standard datasets demonstrate that the proposed model provides an effective way of producing pixel-wise dense image labeling.

Citations

• The Pascal Visual Object Classes (VOC) Challenge
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Holistically-Nested Edge Detection
• Learning Deconvolution Network for Semantic Segmentation

Cited by

• DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories
• Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
• ACFNet: Attentional Class Feature Network for Semantic Segmentation
• Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
• Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness

Related

• Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
• Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation
• Coarse-to-fine Semantic Segmentation from Image-level Labels
• Automatic Image Labelling at Pixel Level
• Error Correction for Dense Semantic Image Labeling