# facebookresearch/DomainBed

DomainBed is a suite to test domain generalization algorithms

Repository: https://github.com/facebookresearch/DomainBed
Canonical: https://ross.abutalabs.com/products/domainbed
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2025-12-16T17:09:28+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 35, longevity 100
- inputs: {"age_days": 2256, "days_push": 260, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1630, forks 329 (observed 2026-08-28T04:05:13.959352+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, benchmarking
- domain: machine-learning, computer-vision
- platform: python
- tags: domain-generalization, pytorch, benchmark-suite, out-of-distribution, research, gpu

## Member repositories
- facebookresearch/DomainBed (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:13.959352+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:47:55.673318+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/DomainBed (fetched 2026-08-28T04:05:13.959352+00:00, sha c8d5d1a5861e)
- Data as of 2026-08-30T08:39:29.467469+00:00.