SC-CAM
SC-CAM copied to clipboard
Datasets used
Hi Do you only use the Pascal Voc 2012 dataset with 2900 images What about the augmented data set that has over 10000+ images here: http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz
I see in your paper you mention using the augmented dataset, but I dont see it being referenced anywhere. Where do I place it if i want to use those images as well?
There is a train_aug.txt
in the script.
can we get a link from where these additional 10000+ images are downloaded?