AI Paper Atlas

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

From Big to Small: Adaptive Learning to Partial-Set Domains

Zhangjie Cao, Kaichao You, Ziyang Zhang, Jianmin Wang, Mingsheng Long

TPAMI 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 39 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 instance selection with shared layers to source-only ResNet (ablation)ResNet · Office-31 PDA ablation (6 tasks avg)accuracy (%): 87.05 -> 91.05Improved
add class selection (ablation)SAN++ variant · Office-31 PDA ablation (6 tasks avg)accuracy (%): 91.05 -> 93.24Improved
add entropy minimization (ablation)SAN++ variant · Office-31 PDA ablation (6 tasks avg)accuracy (%): 93.24 -> 95.32Improved
replace entropy minimization with self-training (ablation)SAN++ · Office-31 PDA ablation (6 tasks avg)accuracy (%): 95.32 -> 97.89Improved
share bottom layers of the multitask discriminator (ablation)SAN++ · Office-31 PDA ablation (6 tasks avg)accuracy (%): 97.02 -> 97.89Improved
share bottom layers of the multitask discriminator (ablation)SAN++ · Office-31 I->C costpeak GPU memory (MB): 5551.0 -> 569.5Improved
share bottom layers of the multitask discriminator (ablation)SAN++ · Office-31 I->C costtime (s): 1.601 -> 0.148Improved
add complement entropy (COT) lossSAN++ · Office-Home PDA (12 tasks avg)accuracy (%): 75.96 -> 77.37Improved
add complement entropy (COT) lossSAN++ · VisDA-2017 PDAaccuracy (%): 63.06 -> 76.94Improved
add complement entropy (COT) lossSAN++ · Office-31 PDA (6 tasks avg)accuracy (%): 97.89 -> 98.18Improved
use SAN++ instead of SANSAN · Office-Home PDA (12 tasks avg)accuracy (%): 65.30 -> 75.96Improved
use SAN++ instead of SANSAN · VisDA-2017 PDAaccuracy (%): 49.92 -> 63.06Improved

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