yun-liu / RCF

Richer Convolutional Features for Edge Detection
Other
761 stars 259 forks source link

The training dataset used for BSDS500 #102

Open zc08 opened 5 years ago

zc08 commented 5 years ago

Thank you so much for releasing the code!

I have a question concerning the training data used for BSDS500 dataset. In the HED (Holistic edge detection) paper, they used only augmented data from the BSDS500 training and validation dataset; but it seems for RCF, both BSDS data and Pascal data are used for training.

Does RCF still perform better than HED when trained with BSDS500 data only?

yun-liu commented 5 years ago

We have performed this experiment in the paper. RCF performs better than HED with only BSDS500 dataset for training. Please refer to the paper for details!