SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.01434 · 2020

In Search of Lost Domain Generalization

Ishaan Gulrajani, David Lopez-Paz

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
facebookresearch/DomainBed canonical 0 of 2
matsuolab/t3a extension 2 of 3
kowshikthopalli/DREAME extension 1 of 1
copy not recorded — 0 of 1
FunctionStatusWhere it lives
accuracy_ent Ran matsuolab/t3a/domainbed/scripts/unsupervised_adaptation.py
code served (permissive licence) · get_code("5d1f700db67751f1")
inv_lr_scheduler Ran kowshikthopalli/DREAME/domainbed/algorithms.py
code served (permissive licence) · get_code("3ce1df52d4a961b8")
softmax_entropy Ran matsuolab/t3a/domainbed/scripts/unsupervised_adaptation.py
code served (permissive licence) · get_code("e6171e29ed623a12")
generate_featurelized_loader Not yet run matsuolab/t3a/domainbed/scripts/unsupervised_adaptation.py
code served (permissive licence) · get_code("57634636fcd54537")
get_algorithm_class Not yet run this paper's copy was not recorded; identical code first harvested from facebookresearch/domainbed
pointer only · get_code("b0bc80b1655a6802")
get_dataset_class Not yet run facebookresearch/DomainBed/domainbed/datasets.py
code served (permissive licence) · get_code("d0ea85d74c20dea9")
num_environments Not yet run facebookresearch/DomainBed/domainbed/datasets.py
code served (permissive licence) · get_code("73f32252eedba6a4")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The goal of domain generalization algorithms is to predict well on distributions different from those seen during training. While a myriad of domain generalization algorithms exist, inconsistencies in experimental conditions-datasets, architectures, and model selection criteria-render fair and realistic comparisons difficult. In this paper, we are interested in understanding how useful domain generalization algorithms are in realistic settings. As a first step, we realize that model selection is non-trivial for domain generalization tasks. Contrary to prior work, we argue that domain generalization algorithms without a model selection strategy should be regarded as incomplete. Next, we implement DOMAINBED, a testbed for domain generalization including seven multi-domain datasets, nine baseline algorithms, and three model selection criteria. We conduct extensive experiments using DO-MAINBED and find that, when carefully implemented, empirical risk minimization shows state-of-the-art performance across all datasets. Looking forward, we hope that the release of DOMAINBED, along with contributions from fellow researchers, will streamline reproducible and rigorous research in domain generalization. * Alphabetical order, equal contribution. Preprint. Under review.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.01434")
get_code_for_paper("2007.01434")
have("2007.01434")

Connect an agent — have() is free.