1
$\begingroup$

I am working on to implement the approach in the paper https://arxiv.org/pdf/1603.03101v1.pdf on detecting text in wild using recursive convolution neural net and attention modelling. Being a bit new to deep nets and have developed the following interpretation about the recursive CNN given in the paper:

It is given in the paper that while training could be done by " reusing the same convolutional weight matrix multiple times at each layer." Does this means the following thing in the pseudo code below

layer1:

iterating multiple times over { train convolution_layer(weights) with labels }

layer2:

iterating multiple times over { train convolution_layer(weights) with labels }

Here in the consecutive iteration in a layer we use weights of previous iteration. We use different weight initialisation for different layers here

While using the network for test set, we will input the weights we got from the last iterations. Please comment on this interpretation and I would be grateful if anyone could suggest some links and literature for the same. Thank you!

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.