AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Selecting Data Augmentation for Simulating Interventions

Maximilian Ilse, Jakub M Tomczak, Patrick Forré

ICML 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 21 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Apply random rotations selected by SDAERM on Rotated MNIST · Rotated MNIST averageaccuracy: 88.3 -> 95.9Improved
Apply hue and translation augmentation selected by SDAERM on Colored MNIST · Colored MNIST testaccuracy: 68.7 $\pm$ 0.9 -> 74.1 $\pm$ 0.9Improved
Apply color perturbations selected by SDAERM on PACS · PACS averageaccuracy: 73.4 -> 74.9Improved
Apply selected color perturbationsERM on PACS · PACS cartoonaccuracy: 71.7 -> 68.49Hurt
Apply selected color perturbationsERM on PACS · PACS photoaccuracy: 91.1 -> 88.35Hurt
Use all listed augmentations instead of SDA-selected augmentations (ablation)SDA on Rotated MNIST · Rotated MNIST averageaccuracy: 95.9 -> 70.5Hurt
Use all listed augmentations instead of SDA-selected augmentations (ablation)SDA on Colored MNIST · Colored MNIST testaccuracy: 74.1 -> 65.4Hurt
Use all listed augmentations instead of SDA-selected augmentations (ablation)SDA on PACS · PACS averageaccuracy: 74.9 -> 58.8Hurt
Expand the rotation range from [-15°, 15°] to [0°, 359°] (ablation)Rotation augmentation selection on Rotated MNIST · Rotated MNIST domain-classifier selectiondomain accuracy: 92.60 $\pm$ 0.98 -> 51.70 $\pm$ 2.21Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy