SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04030 · ICML · 2021

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

Ling Shao, Xiantong Zhen, Cees Snoek, Zehao Xiao, Jiayi Shen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 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
zzzx1224/A-Bit-More-Bayesian — 2 of 2
FunctionStatusWhere it lives
BayesLinear_Normalq Ran zzzx1224/A-Bit-More-Bayesian/pacs_code/pacs_model.py
pointer only (licence: NONE) · get_code("f579fec5e726fc79")
isotropic_gauss_loglike Ran zzzx1224/A-Bit-More-Bayesian/pacs_code/pacs_model.py
pointer only (licence: NONE) · get_code("8f7bd9dcece040ec")

Repositories linked to this paper

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

Abstract

Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference, by incorporating uncertainty into neural network weights. We couple domain invariance in a probabilistic formula with the variational Bayesian inference. This enables us to explore domain-invariant learning in a principled way. Specifically, we derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network. We empirically demonstrate the effectiveness of our proposal on four widely used cross-domain visual recognition benchmarks. Ablation studies validate the synergistic benefits of our Bayesian treatment when jointly learning domain-invariant representations and classifiers for domain generalization. Further, our method consistently delivers state-of-the-art mean accuracy on all benchmarks.

For agents

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

get_harvested_code_for_paper("2105.04030")
get_code_for_paper("2105.04030")
have("2105.04030")

Connect an agent — have() is free.