Methods › Computer Vision › Image Scaling Strategies › FixRes

FixRes

10 papers tagged archive 2025-07-28

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.

PaperSource

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.

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.

TaskPapers
Image Classification9
image-classification7
Data Augmentation5
Fine-Grained Image Classification4
General Classification4
Semantic Segmentation2
Document Image Classification1
Document Layout Analysis1
Efficient ViTs1
Few-Shot Image Classification1
Few-Shot Learning1
Knowledge Distillation1
Language Modeling1
Language Modelling1
Out-of-Distribution Generalization1
Representation Learning1
Self-Supervised Learning1
Transfer Learning1

Usage over time archive 2025-07-28

Papers per year tagged with FixRes: 2019 to 2022, peak 5 5 0 2019: 3 papers 2019 2020: 5 papers 2020 2021: 0 papers 2021 2022: 2 papers 2022
Papers per year the archive tags with this method, by the paper's archive date (10 dated). Bars are counts, not a trend claim.

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

Image Scaling Strategies

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