Receptive Field Calculator

We built a tool for calculating the receptive field of convolutional filters:  #deeplearning

  • A convolutional layer operates over a local region of the input to that layer with the size of this local region usually specified directly.
  • You can also compute the effective receptive field of a convolutional layer which is the size of the input region to the network that contributes to a layers’ activations.
  • For example, if the first convolutional layer has a receptive field of 3×3 then it’s effective receptive field is also 3×3 since it operates directly on the input.
  • However if the second layer of a convolutional network also has a 3×3 filter, then it’s (local) receptive field is 3×3, but it’s effective receptive field is 5×5.

A convolutional layer operates over a local region of the input to that layer with the size of this local region usually specified directly. You can also compute the effective receptive field of a convolutional layer which is the size of the input region to the network that contributes to a layers’ activations. For example, if the first convolutional layer has a receptive field of 3×3 then it’s effective receptive field is also 3×3 since it operates directly on the input.
Continue reading “Receptive Field Calculator”

[1604.03539] Cross-stitch Networks for Multi-task Learning

Cross-stitch networks for multi-task learning  #deeplearning #computervision #CVPR2016

  • A network with cross-stitch units can learn an optimal combination of shared and task-specific representations.
  • We propose a new sharing unit: “cross-stitch” unit.
  • The units combine the activations from multiple networks and can be trained end-to-end.
  • In the paper, we propose a principled approach to learn shared representations in ConvNets using multi-task learning.
  • Abstract: Multi-task learning in Convolutional Networks has displayed remarkable success in the field of recognition.

Read the full article, click here.


@quantombone: “Cross-stitch networks for multi-task learning #deeplearning #computervision #CVPR2016”


One hundred percent of your contribution will fund improvements and new initiatives to benefit arXiv’s global scientific community. Please join the Simons Foundation and our generous member organizations and research labs in supporting arXiv.


[1604.03539] Cross-stitch Networks for Multi-task Learning