efficient instance-aware test-time augmentation method resulting in significant gains over previous approaches

We would like to thank you for your thorough evaluation, helpful suggestions, and comments. We trained our loss predictor for five crop areas. Compared to the 5-crop ensemble, choosing one transform by our method gives almost the same performance, and selecting the two transforms achieves even better performance with less computational cost. Figure 2: Comparison for the same GPS transforms on the clean ImageNet set using ResNet-50. We trained our loss predictor on the searched GPS policies to choose ones specific for each test instance.