AI Paper Atlas

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

Representation Learning with Multiple Lipschitz-Constrained Alignments on Partially-Labeled Cross-Domain Data

Songlei Jian, Liang Hu, Longbing Cao, Kai Lu

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 3 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 complementary representation with self alignment loss LSA (ablation)MULANCom · VisDA semi-supervised DA, 10% labeledaccuracy (%): 77.44±0.2 -> 78.11±0.1Improved
add self alignment LSA (ablation)MULANCom · VisDA semi-supervised DA, 20% labeledaccuracy (%): 78.48±0.2 -> 79.15±0.2Improved
add self alignment LSA (ablation)MULANCom · VisDA semi-supervised DA, 50% labeledaccuracy (%): 79.76±0.1 -> 80.64±0.1Improved
use common representation (class + distribution alignment) vs TADT baselineMULANCom · VisDA semi-supervised DA, 10% labeledaccuracy (%): 69.68±0.4 -> 77.44±0.2Improved
increase labeled source data from 10% to 50%Source-only · VisDA semi-supervised DAaccuracy (%): 45.01±1.0 -> 38.82±0.5Hurt
increase labeled data from 10% to 50%MULAN · VisDA semi-supervised DAaccuracy (%): 78.11±0.1 -> 80.64±0.1Improved
use complementary representation with target classifier instead of common representation with source classifier (ablation)MULAN · VisDA few-shot DA, 5-shotaccuracy (%): 56.02 -> 57.97Improved
use complementary representation instead of common representation (ablation)MULAN · VisDA few-shot DA, 10-shotaccuracy (%): 58.17 -> 62.29Improved
use complementary representation instead of common representation (ablation)MULAN · VisDA few-shot DA, 20-shotaccuracy (%): 64.40 -> 66.73Improved
MULAN complementary representation vs Target-only classifierMULAN · VisDA few-shot DA, 5-shotaccuracy (%): 41.17 -> 57.97Improved
reduce shots from 20 to 5MULAN(Comp) · VisDA few-shot DAaccuracy (%): 66.73 -> 57.97Hurt
reduce shots from 20 to 5DANN · VisDA few-shot DAaccuracy (%): 38.21 -> 35.27Hurt

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