search

mala-lab / ADShift

Official PyTorch implementation of the ICCV'23 paper “Anomaly Detection under Distribution Shift”
26 stars 4 forks source link

How should we partition the dataset, such as the PACS dataset? #3

Open EIPsilly opened 1 year ago

EIPsilly commented 1 year ago

How should we partition the dataset, such as the PACS dataset? What should be the split ratios, and what random seed to use

caothientri2001vn commented 9 months ago

You can download the PACS dataset through the link I provided and get the default of partition.

latharam commented 8 months ago

Can you clarify further what do you mean by default partition? Do you mean the text files at PACS/pacs_label/photo_test_kfold.txt, PACS/pacs_label/photo_train_kfold.txt and PACS/pacs_label/photo_crossval_kfold.txt ? The PACS/pacs_label/photo_test_kfold.txt, and PACS/pacs_label/photo_crossval_kfold.txt seem to have a lot of images in common!

Much appreciate detailed response on how to setup the data for PACS to replicate your results