PaDiM
PaDiM copied to clipboard
PaDiM Shared Performance
How much is the difference in performance compare to original PaDiM?
I think it really depends on the kind of images you are dealing with.
For texture images where the normal data has a small number of modalities then a shared variant may be good enough.
For objects where the location is the patches are very different based on their location on the image then it won't work as well.
Doing a quick test on 2 mvtec datasets:
Dataset | PRO Score | ROCAUC |
---|---|---|
Tile (texture) | 86% | 84% |
Pill (objects) | 82% | 44% |
The main advantage being the much smaller memory footprint and not really performance.
How much did you test batch size
? Wouldn't the performance be close if it was a little large test batch size?
I won't expect the batch size to have any impact on the performance since batch samples don't interact with each other. What impact do you think it could have ?
I'll leave it after a test