AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions With Superior OOD Generalization

Damien Teney, Ehsan Abbasnejad, Simon Lucey, Anton van den Hengel

CVPR 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 34 citations (OpenAlex)

This paper tried a common change: Add dropout

Add dropout rather than use independent-seed baseline · MNIST/CIFAR collages, average · accuracy: 62.7 -> 65.3 No clear effect

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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
Train a collection with input-gradient diversity regularization rather than independent seeds2-hidden-layer MLP · MNIST/CIFAR collages, average across four held-out-block testsaccuracy: 62.7 -> 78.5Improved
Train a collection with input-gradient diversity regularization rather than the strong baselineFrozen ResNet-50, 2-layer MLP · BARbest single-model accuracy: 64.9 -> 67.1Improved
Train with input-gradient diversity regularization rather than without itFrozen ResNet-50, 2-layer MLP · BARensemble accuracy: 63.1 -> 66.1Improved
Train a collection with input-gradient diversity regularization rather than independent seedsResNet-18 · PACS artbest single-model accuracy: 85.71 -> 86.80Improved
Train a collection with input-gradient diversity regularization and select on PACSResNet-18 · VLCS horse/personAUC: 74.57 -> 79.66Improved
Use diversity regularization rather than independent random seedsResNet-18 · PACS averageaccuracy: 82.9 -> 84.2Improved
Increase the collection from 8 to 96 models (ablation)2-hidden-layer MLP · MNIST/CIFAR collages, averageaccuracy: 73.7 -> 78.5Improved
Increase the collection from 16 to 96 models (ablation)2-hidden-layer MLP · MNIST/CIFAR collages, averageaccuracy: 72.9 -> 78.5Improved
Increase the collection from 32 to 96 models (ablation)2-hidden-layer MLP · MNIST/CIFAR collages, averageaccuracy: 76.9 -> 78.5Improved
Increase the collection from 64 to 96 models (ablation)2-hidden-layer MLP · MNIST/CIFAR collages, averageaccuracy: 77.0 -> 78.5Improved
Use 16 instead of 8 models (ablation)Proposed collage collection · MNIST/CIFAR collages, averageaccuracy: 73.7 -> 72.9No clear effect
Add dropout rather than use independent-seed baseline (ablation)2-hidden-layer MLP · MNIST/CIFAR collages, averageaccuracy: 62.7 -> 65.3No clear effect

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