Jeremy Howard: Using smaller images in training first works great, but is still largely unknown.

Jeremy called that idea "progressive resizing". Knowing that starting from smaller images turns out to accelerate learning and results in better generalizations, an even more precise term for this technique would seem to be "progressive upsizing".

One of his findings were that going much below 64x64 image size tends not to help very much. Jeremy concluded:

It's a great technique and I definitely try a few different sizes.

Source: Lesson 3: Deep Learning 2019 - Data blocks; Multi-label classification; Segmentation