Corpus ID: 9609915

RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation

@inproceedings{Lin2016RefineNetM,
  title={RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation},
  author={Guosheng Lin and A. Milan and Chunhua Shen and I. Reid},
  year={2016}
}

Guosheng Lin, A. Milan, +1 author I. Reid

Published 2016

Computer Science

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along… CONTINUE READING

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed