Deep Learning based edge detection using holistically nested edge detection (HED)
Code generated in the video can be downloaded from here:
github.com/bnsreenu/python_fo...
All other code:
github.com/bnsreenu/python_fo...
Original HED paper: arxiv.org/pdf/1504.06375.pdf
Caffe model is encoded into two files
1. Proto text file: github.com/s9xie/hed/blob/mas...
2. Pretrained caffe model: vcl.ucsd.edu/hed/hed_pretraine...
NOTE: In future, if these links do not work, I cannot help. Please Google
and find updated links (information current as of October 2022)
HED is a deep learning model that uses fully convolutional neural networks and deeply-supervised nets to do image-to-image prediction.​
The output of earlier layers is called side output. ​
HED makes use of the side outputs of intermediate layers. ​
The output of all 5 convolutional layers is fused to generate the final predictions. ​
Since the feature maps generated at each layer is of different size, it’s effectively looking at the image at different scales. ​
The model is VGGNet with few modifications:​
Side output layer is connected to the last convolutional layer in each stage, respectively conv1_2, conv2_2, conv3_3, conv4_3,conv5_3. The receptive field size of each of these convolutional layers is identical to the corresponding side-output layer.​
Last stage of VGGNet is removed including the 5th pooling layer and all the fully connected layers.​
The final HED network architecture has 5 stages, with strides 1, 2, 4, 8 and 16, respectively, and with different receptive field sizes, all nested in the VGGNet. ​