Under review as a conference paper at ICLR 2020 completely free-form sampling in image space : Spatial Transformers

2019

Subfields: Computer Vision and Pattern Recognition, Model Architectures

Citations in the corpus

• On the Selection of Initialization and Activation Function for Deep Neural Networks (2018, background): “Additional simulations results on diverse datasets demonstrating better performance of Swish over many other activation functions can be found in Ramachandran et al. (2017) (Notice that these authors have already implemented Swish in Tensorflow).”