AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

Alexandre Rame, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Leon Bottou, David Lopez-Paz

ICML 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 5 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
Recycle diverse auxiliary fine-tunings as separate target-task initializations, then average the target-fine-tuned weightsModel soups · PACSaccuracy: 88.7 ± 0.2 -> 89.5 ± 0.1Improved
Recycle diverse auxiliary fine-tunings as separate target-task initializations, then average the target-fine-tuned weightsModel soups · VLCSaccuracy: 79.1 ± 0.1 -> 78.5 ± 0.1Hurt
Recycle diverse auxiliary fine-tunings as separate target-task initializations, then average the target-fine-tuned weightsModel soups · OfficeHomeaccuracy: 72.1 ± 0.2 -> 73.1 ± 0.1Improved
Recycle diverse auxiliary fine-tunings as separate target-task initializations, then average the target-fine-tuned weightsModel soups · TerraIncaccuracy: 51.4 ± 0.6 -> 51.8 ± 0.4Improved
Recycle diverse auxiliary fine-tunings as separate target-task initializations, then average the target-fine-tuned weightsModel soups · DomainNetaccuracy: 47.4 ± 0.2 -> 47.5 ± 0.1No clear effect
Recycle diverse auxiliary fine-tunings as separate target-task initializations, then average the target-fine-tuned weightsModel soups · DomainBed Avgaccuracy: 67.6 -> 68.1Improved
Use greedy rather than uniform weight selection (ablation)Model ratatouille · TerraIncaccuracy: 51.8 ± 0.4 -> 49.2 ± 0.9Hurt
Increase the number of auxiliary tasks (ablation)Model ratatouille · DomainBed OOD test domainsaccuracyImproved
Use auxiliary-task recycling instead of extending target fine-tuning alone (ablation)Model ratatouille vs. model soups · OfficeHome, Art OOD domainaccuracyImproved
Increase the number of target fine-tuning runs (ablation)Model ratatouille · DomainBed OOD test domainsaccuracyImproved
Use moving-average checkpoints for auxiliary-task initializations (ablation)Model ratatouille · DomainBed Avgaccuracy: 68.1 -> 68.2No clear effect

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