search

kaixin96 / PANet

Code for our ICCV 2019 paper PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
320 stars 64 forks source link

Regarding the Data Splits #34

Closed ahatamiz closed 4 years ago

ahatamiz commented 4 years ago

Hello, thanks for publicly sharing the code of your paper. I was going over the config.py file to see if the default setting match what is reported in the paper, but noticed that n_runs = 5. Shouldn't it be set to 4 as the reported accuracy is apparently for 4 splits ?

I am under the assumption that for each run, the number reported in the paper (e.g. split-1 for run 0, split-2 for run 1 etc.) is the meanIoU as printed in the outputs of test.py. And by setting label_sets = 0 , one should be able to run the inference on the same splits as reported in the paper ( and seemingly by setting n_runs = 4 as commented in the above. I Would appreciate some clarification.

kaixin96 commented 4 years ago

Hi @ahatamiz , label_sets = 0, 1, 2, 3 correspond to split-1, 2, 3, 4. n_runs = 5 means 5 runs with different random seeds (but same split) and each run consists of 1000 testing episodes. This is meant to make the results more stable, as mentioned in Section 4.1 of our paper. Thank you.

ahatamiz commented 4 years ago

@kaixin96 Thank you. It makes sense.