AI Paper Atlas

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

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

Dapeng Hu, Jian Liang, Jun Hao Liew, Chuhui Xue, Song Bai, Xinchao Wang

NeurIPS 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 2 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 MixVal instead of SourceVal for model selectionUDA model selection · VisDAvalidation accuracy (%): 71.04 -> 77.86Improved
use MixVal instead of SND for model selectionUDA model selection · Office-Homevalidation accuracy (%): 66.02 -> 69.84Improved
use MixVal instead of SND for model selectionBNM · DomainNetvalidation accuracy (%): 56.93 -> 67.85Improved
use MixVal instead of Entropy for model selectionDANCE open-partial-set · Office-HomeHOS (%): 34.27 -> 67.01Improved
use MixVal instead of Entropy for model selectionSHOT source-free · VisDAaccuracy (%): 82.65 -> 83.12Improved
use MixVal instead of SND for model selection with two hyperparametersMDD · Office-Homevalidation accuracy (%): 57.42 -> 70.25Improved
use MixVal instead of SND for model selection with two hyperparametersMCC · Office-Homevalidation accuracy (%): 69.96 -> 73.75Improved
use MixVal instead of SND for validating mixup-based UDADMRL · Office-31validation accuracy (%): 77.55 -> 78.16Improved
use MixVal instead of SND on a segmentation taskAdaptSeg · GTAV to CityscapesmIoU (%): 40.69 -> 42.20Improved
use MixVal instead of Entropy with ViT-B backboneBNM · DomainNet R to Svalidation accuracy (%): 28.21 -> 54.78Improved
use Entropy instead of SourceVal for segmentation model selectionAdvEnt · GTAV to CityscapesmIoU (%): 39.08 -> 38.41Hurt
use RV instead of SourceVal for partial-set model selectionPADA · Office-Home partial-setvalidation accuracy (%): 58.87 -> 58.34Hurt

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