2019 · 12 citations · 16 references
ComputingComputer ScienceComputer VisionMachine LearningRemote SensingDeep LearningImagingConvolutional Neural NetworksImage Super-resolutionSuper-resolutionSuper-resolution ImagingSuper-resolution MappingSuper-resolution ProcessingSuper-resolution ReconstructionTarget Detection
Enhancing the resolution of SAR image can significantly improve more complicated application such as automatic target detection. This paper proposes a new algorithm to reconstruct super-resolution image by using a deep residual SqueezeNet. It directly achieves end to end mapping from the low-resolution image to a high-resolution image with the convolutional neural network. The lightweight SqueezeNet with fewer parameters but equivalent accuracy compared to a well-known model is used to reduce the computational complexity. Moreover, inspired by ResNet, we utilize the residual learning method with high learning rates to accelerate convergence. Experimental results demonstrate that the new algorithm brought forward in this paper not only has lightweight construction, but also can be faster, and get similar or better results than state-of-the-art methods.
16
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Christian Ledig, Lucas Theis, Ferenc Huszár et al. · 2017 · 12.3K citations