AI Paper Atlas

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

Heterogeneous Transfer Learning with Weighted Instance-Correspondence Data

Yuwei He, Xiaoming Jin, Guiguang Ding, Yuchen Guo, Jungong Han, Jiyong Zhang, Sicheng Zhao

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 8 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 meta-learner updates of the feature transformation (ablation)TLWCsup · Webis-CLS-10 EJMaccuracy (%): 79.04 -> 80.94Improved
add meta-learner updates of the feature transformation (ablation)TLWCsup · Webis-CLS-10 EFBaccuracy (%): 84.92 -> 84.50Hurt
add meta-learner updates of the feature transformation (ablation)TLWCsup · Webis-CLS-10 EFDaccuracy (%): 84.41 -> 85.00Improved
add meta-learner updates of the feature transformation (ablation)TLWCsup · MRC FRaccuracy (%): 76.47 -> 78.70Improved
add meta-learner updates of the feature transformation (ablation)TLWCsup · MRC ITaccuracy (%): 61.77 -> 68.83Improved
add meta-learner updates of the feature transformation (ablation)TLWCsup · MRC GEaccuracy (%): 71.10 -> 70.08Hurt
add meta-learner updates of the feature transformation (ablation)TLWCsup · MRC SPaccuracy (%): 67.37 -> 69.40Improved
TLWC instead of HHTLHHTL · MRC ITaccuracy (%): 61.80 -> 68.83Improved
TLWC instead of HHTLHHTL · Webis-CLS-10 EJMaccuracy (%): 79.32 -> 80.94Improved
TLWC instead of HHTLHHTL · MRC GEaccuracy (%): 69.47 -> 70.08Improved
deep-model features (HHTL) instead of DATNDATN · Webis-CLS-10 EFBaccuracy (%): 78.47 -> 83.63Improved
learned IC weights under artificial mismatch noise (n_e up to 32)TLWCsup · text->DeCAF6 NUS-WIDEaccuracy (%)Improved

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