Open weitianhan opened 7 years ago
I just extract superpixels on 150*100 image.
@lemondan , thanks for your reply. In your Co-CNN paper, in the upsampling operations in the global-to-local stage, are you just doing bilinear upsampling without learning parameters in deconvolution layers?
For that co-cnn paper, Yes.
Hi @lemondan, I would like to ask how do you determine the final output in the Co-cnn paper. For example the output of the network are C probability maps, then for each pixel, are you classifing the pixel into the class with the highest probability? And I notice that you use entropy rate segmentation for post-processing, so do you implement your network with Matlab API of Caffe?
@lemondan , would you please give some hints about how do you do back-propagation in the superpixel layers?
Thank you so much for providing the dataset. I want to ask is there any convenient way to resize the image but still keeping the superpixel information. Just like what you have done in your paper, you resize the image to 150*100 before training.