2014 Fully Convolutional Network (FCN) Paper summary

Thank you very much! It helped me a lot to understand the paper!

Hello sir that was an amazing explanation. I'm currently doing mechanical engineering bacherlor degree and would love to work on Autonomous vehicles and work on the software side of things. Do you have any career guidance.

very informative and better to understand than the original paper. Thank you!

thanks for your summary, this thing is very strange for me but you help me understand and image it

Thank you very much!!!

Your explenation of convolutionlizatiobn is totally wrong because convolution is scaling down the image by constant factor so when using 1x1 convolution final vector will also be of arbitrary size not always 1x1xD

Hello, thanks for that clear explanation.
I just have a question about cnn. Does the size of the output Feature maps from cnn matters. Like if the output feature map size is large will it affect the classifier (fully connected layers). Or it’s better to make the output feature map small? If I make it large will it affect the accuracy or it will be same as small features maps (and I can make that by making cnn layers to keep the image size to be same so It will not decrease the size of the image )And thanks

Amazing explanation thank you

Please continue doing this type of video.

講得太好了，謝謝你!!

Thanks for the video! I had difficulties while reading the papers but you break it down really nicely!

You are doing amazing job with these papers explanations, thank you =) Btw, would be great to see your summary on Mask R-CNN.

Hi! Can you make a video on the 'Meta Pseudo Labels' paper. Your paper summary videos are awesome