TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation

@article{Iglovikov2018TernausNetUW,
  title={TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation},
  author={Vladimir I. Iglovikov and Alexey Shvets},
  journal={CoRR},
  year={2018},
  volume={abs/1801.05746}
}
Pixel-wise image segmentation is demanding task in computer vision. Classical U-Net architectures composed of encoders and decoders are very popular for segmentation of medical images, satellite images etc. Typically, neural network initialized with weights from a network pre-trained on a large data set like ImageNet shows better performance than those trained from scratch on a small dataset. In some practical applications, particularly in medicine and traffic safety, the accuracy of the models… CONTINUE READING