AI Paper Atlas

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

A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation

Jian Liang, Yunbo Wang, Dapeng Hu, Ran He, Jiashi Feng

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 107 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 balanced adversarial alignment (target augmentation with source samples) to E-DANN (ablation)E-DANN · Office-Home partial DAaccuracy (avg): 70.24 -> 73.40Improved
add balanced adversarial alignment to E-DANN (ablation)E-DANN · Office31 partial DAaccuracy (avg): 95.60 -> 96.20Improved
add balanced adversarial alignment to E-DANN (ablation)E-DANN · ImageNet-Caltech partial DAaccuracy (avg): 78.00 -> 81.16Improved
add adaptive complement entropy (uncertainty suppression) to BAA (ablation)Ours (w/ BAA) · Office-Home partial DAaccuracy (avg): 73.40 -> 75.98Improved
add adaptive complement entropy to BAA (ablation)Ours (w/ BAA) · Office31 partial DAaccuracy (avg): 96.20 -> 97.81Improved
add adaptive complement entropy to BAA (ablation)Ours (w/ BAA) · ImageNet-Caltech partial DAaccuracy (avg): 81.16 -> 83.68Improved
add uncertainty suppression to closed-set DA (ablation)Ours (w/ BAA) · Office-Home closed-set DAaccuracy (avg): 67.6 -> 68.7Improved
add uncertainty suppression to closed-set DA with CDAN (ablation)Ours (w/ BAA)+CDAN · Office-Home closed-set DAaccuracy (avg): 68.0 -> 69.2Improved
add balanced adversarial alignment to closed-set DA (ablation)DANN-based · Office-Home closed-set DAaccuracy (avg)No clear effect
use adaptive complement entropy (xi=0.3) instead of plain complement entropy (xi=0) (ablation)BA3US · Office-Home partial DAaccuracy (avg): 75.32 -> 76.28Improved
use adaptive complement entropy (xi=0.9) instead of xi=0 (ablation)BA3US · Office31 partial DAaccuracy (avg): 97.68 -> 97.84No clear effect
set beta=10.0 instead of 1.0 (ablation)BA3US · Office-Home partial DAaccuracy (avg): 75.98 -> 73.25Hurt

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