Jianzhong He
Jianzhong He
Yes, we did augment with Pascal Context while training.
Yes, we indeed use the semantic class boundaries of Pascal Context to augment the training data. Moreover, we also do augmentation on the pascal context to further increase the training...
Yes, the lst file just provide the list of file to be infered. And the second column will not be used when evaluation. The reason to this is that i...
I follows the HED and using the code of BSDS500 benchmark.
you have to download corresponding datasets and change the path_to/bsds500/BSR/BSDS500/data/ to that dir. The test_id.txt is the list of that datatset. voc_valtest.txt is the valdation list of voc2012 we used...
We use the valid.txt
Hi, Thanks for your attention, I use the code like as below https://github.com/pdollar/edges/blob/master/private/edgesNmsMex.cpp
The path_to should change to the directory that your local dir, rather the path_to/*, *e.g.*, /home/users/datasets/bsds500/BSR/BSDS500/data/test_pair.lst. Note that, you must prepare the test_pair.lst ahead before.
Thanks for your attention of our work. We have shown the training details in implement detail which using data augmentation same as HED, and the hyperparamter yita is 0.3. Moreover,...
@ForawardStar We used the Pascal VOC Context(also called Pascal Context) for augmentation. It can be obtained from the official website https://cs.stanford.edu/~roozbeh/pascal-context/