SSR
SSR copied to clipboard
(NeurIPS 2021) Pytorch implementation of paper "Re-ranking for image retrieval and transductive few-shot classification"
.
I was training the model with my dataset. As the logs say, there were no improvements of mAP during training. Why was that? Or was it because I didn't have...
How to reproduce the work with CUB dataset?
What are `q_g_dist`, `q_q_dist`, `g_g_dist`? And can you please explain how the function `re_ranking_list` works?
I am trying to reproduce your work by training with another dataset. However, my dataset doesn't have ground-truth file such as `good`, `ok`, `bad`, `junk`. How should I train the...