facebookresearch/DomainBed

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1630 stars · 329 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

DomainBed is a PyTorch suite containing benchmark datasets and algorithms for domain generalization research. It implements many algorithms such as ERM, IRM, GroupDRO, CORAL, and DANN with standardized training and evaluation protocols.

Use cases

• benchmark domain generalization algorithms
• compare out-of-distribution generalization methods
• train models on multi-domain datasets like PACS and OfficeHome
• reproduce results from domain generalization papers
• evaluate robustness of models to distribution shift
• add a new domain generalization algorithm to a shared codebase

When to choose

• you need a standardized benchmark for domain generalization research
• you want to compare your method against many published baselines
• you are doing ML research on out-of-distribution robustness

When to avoid

• you need a production-ready training framework
• you only need simple supervised learning without domain shift concerns
• you are not working in PyTorch

Facets

library · maturity active

machine-learning deep-learning benchmarking machine-learning computer-vision python domain-generalization pytorch benchmark-suite out-of-distribution research gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/DomainBed")