search

juhongm999 / hsnet

Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, ICCV 2021
231 stars 43 forks source link

[Question] Domain shift result #19

Closed moonsh closed 2 years ago

moonsh commented 2 years ago

COCO to Pascal - test

I tried to get domain shift results from your pre-trained model (Resnet50 COCO fold 0 ) but strangely got low accuracy.

Please correct me if I am wrong.

For example for the fold 0 in the domain shift test, First, I collect all train and validation pascal data and then exclude all classes that are in the coco fold 0. Only Airplane, Boat, Chair, Dining table, Dog, Person remain for fold 0 as explained in the paper RePRI.

The entire above-remained fold 0 data were used for checking accuracy. There are 7717 cases for the fold 0 test.

Should I sample 1000 cases from 7717 cases?

Thank you.

juhongm999 commented 2 years ago

I shared the code for COCO->PASCAL evaluation. You might want to refer to the data/coco2pas.py

moonsh commented 2 years ago

This helps me a lot. Thank you very much!