Fixing the train-test resolution discrepancy. (arXiv:1906.06423v4 [cs.CV] UPDATED)

Data-augmentation is key to the training of neural networks for image
classification. This paper first shows that existing augmentations induce a
significant discrepancy between the typical size of the objects seen by the
classifier at train and test time. We experimentally validate that, for a
target test resolution, using a lower train resolution offers better
classification at test time.

We then propose a simple yet effective and efficient strategy to optimize the
classifier performance when the train and test resolutions …

arxiv cv test