AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach

Xi Peng, Fengchun Qiao, Long Zhao

TPAMI 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 54 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
add Wasserstein relaxation loss L_relax (ablation)SDG · Digits (train MNIST)average accuracy: 55.43 -> 59.49Improved
add constraint loss L_const (ablation)SDG · Digits (train MNIST)average accuracy: 58.70 -> 59.49Improved
add meta-learning (ablation)SDG · Digits (train MNIST)average accuracy: 58.55 -> 59.49Improved
add meta-learning (ablation)SDG · CIFAR-10-C level 5average accuracy: 64.22 -> 65.59Improved
add Wasserstein relaxation loss (ablation)SDG · CIFAR-10-C level 5average accuracy: 61.92 -> 65.59Improved
add uncertainty quantification to SDGSDG · Digits (train MNIST)average accuracy: 59.49 -> 61.31Improved
add uncertainty quantificationSDG · Digits SYNaccuracy: 48.95 -> 57.14Improved
add uncertainty quantificationSDG · Digits MNIST-Maccuracy: 67.94 -> 67.38Hurt
add uncertainty quantificationSDG · Digits efficiencyparameters / training time: 7.02M -> 5.27M; 23.7min -> 16.4minImproved
use SDG instead of GUDGUD · CIFAR-10-C level 5accuracy: 58.3 -> 65.6Improved
use SDG instead of ERMERM · CIFAR-10-C level 1accuracy: 87.8 -> 90.5Improved
add uncertainty quantificationSDG · SYNTHIA Highway/Dawnavg mIoU: 22.33 -> 23.47Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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