AI Paper Atlas

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

Subspace Identification for Multi-Source Domain Adaptation

Zijian Li, Ruichu Cai, Guangyi Chen, Boyang Sun, Zhifeng Hao, Kun Zhang

NeurIPS 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 12 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
SIG instead of iMSDAMSDA · Office-Home averageaccuracy (%): 76.2 -> 77.8Improved
SIG instead of iMSDAMSDA · ImageCLEF averageaccuracy (%): 90.0 -> 90.3Improved
SIG instead of iMSDAMSDA · PACS averageaccuracy (%): 93.4 -> 93.9Improved
SIG instead of iMSDAMSDA · DomainNet averageaccuracy (%): 47.5 -> 53.0Improved
SIG instead of DRT+STMSDA · DomainNet Sketchaccuracy (%): 60.7 -> 59.5Hurt
remove class-aware alignment loss (ablation)SIG · Office-HomeaccuracyImproved
add reconstruction and KL loss (ablation)SIG · Office-HomeaccuracyImproved
reduce number of domains from 8 to 2 (ablation)Subspace identification · simulationaccuracy: 0.9982 -> 0.5978Hurt
reduce number of domains from 8 to 3 (ablation)SIG theory · simulationRMSE: 0.0433 -> 0.0669Mixed

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