<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
Dear all,<br>
we released the code of the <a
href="https://github.com/nicstrisc/push-pull-cnn-layer">Push-Pull
layer</a>, which can be used as substitute of convolutional layers
in ConvNet architectures, to increase their robustness and
generalization to corruptions of the input images that have not been
seen during training.<br>
<br>
The code is available at <a
href="https://github.com/nicstrisc/push-pull-cnn-layer">https://github.com/nicstrisc/push-pull-cnn-layer
</a><br>
and refers at the paper 'Enhanced robustness of convolutional
networks with a push–pull inhibition layer', which we published open
access at<br>
<a
href="https://link.springer.com/article/10.1007/s00521-020-04751-8">https://link.springer.com/article/10.1007/s00521-020-04751-8</a>.<br>
<br>
We hope this layer can be of use to make ConvNets more robust and to
generalize better to unseen corruptions of the input.<br>
<br>
All the best,<br>
Nicola Strisciuglio<br>
<br>
on behalf of<br>
Manuel Lopez Antequera<br>
Nicolai Petkov
</body>
</html>