I would like to know if it possible to setup a pairwise ranking model using caffe-sl. I am trying to use a model similar to the one described in the paper:
Wang, Jiang, et al. "Learning Fine-grained Image Similarity with Deep Ranking."
But I want to rank face images based on some specific sets of criteria. I have seen that you have a loss function for this. But I am not sure how to set up the prototxt file. If you could give an example that would be quite helpful. Looking forward to you reply.
Hi,
I would like to know if it possible to setup a pairwise ranking model using caffe-sl. I am trying to use a model similar to the one described in the paper: Wang, Jiang, et al. "Learning Fine-grained Image Similarity with Deep Ranking."
But I want to rank face images based on some specific sets of criteria. I have seen that you have a loss function for this. But I am not sure how to set up the prototxt file. If you could give an example that would be quite helpful. Looking forward to you reply.
Thanks,
Naved