AI Paper Atlas

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

Information-Theoretic Domain Adaptation Under Severe Noise Conditions

Wei Wang, Hao Wang, Zhi-Yong Ran, Ran He

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 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
correntropy-based robust adaptation (RIDA) vs l1-norm DTSLRIDA · CMU-PIE with occlusions, meanclassification accuracy (%): 49.57 -> 54.81Improved
RIDA vs DTSL on original CMU-PIERIDA · CMU-PIE original, meanclassification accuracy (%): 63.53 -> 66.73Improved
RIDA vs best non-robust transfer method JDARIDA · CMU-PIE original, meanclassification accuracy (%): 60.24 -> 66.73Improved
RIDA vs non-transfer CESRRIDA · CMU-PIE with occlusions, meanclassification accuracy (%): 48.18 -> 54.81Improved
RIDA vs 1-NN on COIL-20 original C1 vs C2RIDA · COIL-20 original, C1 vs C2classification accuracy (%): 83.61 -> 89.17Improved
RIDA vs JDA on COIL-20 original C1 vs C2RIDA · COIL-20 original, C1 vs C2classification accuracy (%): 89.31 -> 89.17No clear effect
RIDA vs DTSL on COIL-20 original C2 vs C1RIDA · COIL-20 original, C2 vs C1classification accuracy (%): 89.17 -> 88.06Hurt
RIDA vs CESR on P2 vs P4 (similar distributions)RIDA · CMU-PIE original, P2 vs P4classification accuracy (%): 84.53 -> 80.29Hurt
RIDA vs DTSL on P4 vs P3RIDA · CMU-PIE original, P4 vs P3classification accuracy (%): 82.23 -> 91.12Improved
RIDA vs DTSL on P2 vs P4RIDA · CMU-PIE original, P2 vs P4classification accuracy (%): 71.43 -> 80.29Improved
add 50% contiguous occlusions (monkey image) to target dataJDA · CMU-PIE meanclassification accuracy (%): 60.24 -> 36.14Hurt
add occlusions to target dataRIDA · CMU-PIE meanclassification accuracy (%): 66.73 -> 54.81Hurt

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