AI Paper Atlas

Research map / Time series / Causal and generative time series

Diversify: A General Framework for Time Series Out-of-Distribution Detection and Generalization

Lu Wang, Jindong Wang, Xinwei Sun, Yiqiang Chen, Xiangyang Ji, Qiang Yang, Xing Xie

TPAMI 2024 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 52 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
use Diversify instead of the second-best baseline (CORAL)CORAL · EMG OOD detectionID accuracy (%): 76.50 -> 86.32Improved
add Diversify with MCP score over the second-bestGroupDRO-MCP · EMG OOD detectionAUROC / AUPR: +4.67% AUROC, +2.33% AUPRImproved
add Diversify with Mahalanobis score over the second-bestCORAL-MAH · EMG OOD detectionAUROC / AUPR: +14.06% AUROC, +3.94% AUPRImproved
replace MCP with Mahalanobis distance as detection scoreDiversify · USC-HAD X-Person detectionAUROC: 37.50 -> 99.56Improved
use Diversify instead of GroupDROGroupDRO · WESAD OOD detectionID accuracy (%): 59.18 -> 64.37Improved
use Diversify for cross-person generalization on EMGsecond-best method · EMG generalizationaccuracy (%): +4.3%Improved
use Diversify instead of GroupDRO with a basic CNNGroupDRO · Speech Commandsaccuracy (%): over 1% improvementImproved
use Diversify instead of GroupDRO with MatchboxNet3-1-64GroupDRO · Speech Commandsaccuracy (%): over 0.6% improvementImproved
use Diversify for generalization on WESADother state-of-the-art methods · WESAD generalizationaccuracy (%): over 8%Improved
use Diversify for cross-dataset generalizationDANN · HAR cross-dataset generalizationaccuracy (%): 41.2 -> 51.1Improved
use Diversify for one-person-to-another generalizationRSC · HAR one-person-to-anotheraccuracy (%): 55.9 -> 61.7Improved
add pseudo domain labels from class-invariant features (step 3) (ablation)Diversify · EMGaccuracy / AUROCImproved

Later papers that compared with this method

1 later accepted paper reports DIVERSIFY as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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