Giters

icoz69 / CaNet

The code for paper "CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training and Validation Data Question

MSiam opened this issue · comments

commented

Hello
Thanks a lot for sharing the code. I am a bit confused about the setup you used for the metatraining stage. So during the validation you are using the validation data to determine best checkpoint (which in the few-shot setup case would be used as the hold out test set to sample both support and query images). Can you please correct me if there is something I misunderstood in your code and whether this is the correct setup you are using for the paper?

Also how are you evaluating the final numbers reported in your paper to compare with the SOA? Are you using the same exact OSLSM samples pairs ?

Greatly appreciate your efforts.

commented

the original dataset don't have a real val set. i think this code just uses the test set for valiadation. the sampled pairs are random. i think it cannot be completely the same....