Methods › Computer Vision › Image Scaling Strategies › FixRes
FixRes
Introduced by Hugo Touvron et al. in Fixing the train-test resolution discrepancy
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FixRes is an image scaling strategy that seeks to optimize classifier performance. It is motivated by the observation that data augmentations induce a significant discrepancy between the size of the objects seen by the classifier at train and test time: in fact, a lower train resolution improves the classification at test time! FixRes is a simple strategy to optimize the classifier performance, that employs different train and test resolutions. The calibrations are: (a) calibrating the object sizes by adjusting the crop size and (b) adjusting statistics before spatial pooling.
Papers archive 2025-07-28
10 shown of 10, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
DeiT III: Revenge of the ViT 14 Apr 2022 · 12 repositories · arXiv:2204.07118
-
Three things everyone should know about Vision Transformers 18 Mar 2022 · 8 repositories · arXiv:2203.09795Syntology ran 1 of 1 samples · 0 unverified
-
Training data-efficient image transformers & distillation through attention 23 Dec 2020 · 40 repositories · arXiv:2012.12877Syntology ran 12 of 19 samples · 7 unverified · 3 pointer-only (licence)
-
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 · 158 repositories · arXiv:2010.11929Syntology ran 281 of 419 samples · 138 unverified · 154 pointer-only (licence)
-
Circumventing Outliers of AutoAugment with Knowledge Distillation 25 Mar 2020 · 1 repository · arXiv:2003.11342
-
Fixing the train-test resolution discrepancy: FixEfficientNet 18 Mar 2020 · 1 repository · arXiv:2003.08237
-
MaxUp: A Simple Way to Improve Generalization of Neural Network Training 20 Feb 2020 · 1 repository · arXiv:2002.09024Syntology ran 0 of 1 samples · 1 unverified
-
Big Transfer (BiT): General Visual Representation Learning 24 Dec 2019 · 9 repositories · arXiv:1912.11370Syntology ran 3 of 10 samples · 7 unverified
-
Self-training with Noisy Student improves ImageNet classification 11 Nov 2019 · 13 repositories · arXiv:1911.04252Syntology ran 5 of 24 samples · 19 unverified
-
Fixing the train-test resolution discrepancy 14 Jun 2019 · 3 repositories · arXiv:1906.06423Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections