AI Paper Atlas

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

Deep Residual Correction Network for Partial Domain Adaptation

Shuang Li, Chi Harold Liu, Qiuxia Lin, Qi Wen, Limin Su, Gao Ming Huang, Zhengming Ding

TPAMI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 163 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 domain-wise alignment loss L_domain (ablation)DRCN (soft label) · Office-Home partialaccuracy (%): 59.9 -> 68.9Improved
add domain-wise alignment loss L_domain (ablation)DRCN (soft label) · Office-31 partialaccuracy (%): 94.1 -> 94.3Improved
add weighted class-wise alignment loss L_class (ablation)DRCN (soft label) · Office-Home partialaccuracy (%): 61.9 -> 68.9Improved
add weighted class-wise alignment loss L_class (ablation)DRCN (soft label) · Office-31 partialaccuracy (%): 93.3 -> 94.3Improved
use learned class weights instead of all-one weights (ablation)DRCN (soft label) · Office-Home partialaccuracy (%): 64.4 -> 68.9Improved
use learned class weights instead of all-one weights (ablation)DRCN (soft label) · Office-31 partialaccuracy (%): 93.2 -> 94.3Improved
add residual correction block (RCB) (ablation)DRCN (soft label) · Office-Home partialaccuracy (%): 66.3 -> 68.9Improved
add residual correction block (RCB) (ablation)DRCN (soft label) · Office-31 partialaccuracy (%): 93.3 -> 94.3Improved
use hard labels instead of soft labelsDRCN · Office-31 partialaccuracy (%): 94.3 -> 95.9Improved
use soft labels instead of hard labelsDRCN · VisDA2017 + ImageNet-Caltech partialaccuracy (%): 70.8 -> 71.4Improved
use soft labels instead of hard labelsDRCN · Office-Home partialaccuracy (%): 68.5 -> 69.0Improved
use DRCN instead of SAN (best baseline)DRCN · Office-Home partialaccuracy (%): 65.3 -> 69.0Improved

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