AI Paper Atlas

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

Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation

Weichen Zhang, Dong Xu, Wanli Ouyang, Wen Li

TPAMI 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 51 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 image-classifier-based pseudo-label sample selection (CSS) to CAN (ablation)CAN · Office-31 (ResNet50)accuracy: 82.4 -> 88.1Improved
add domain-classifier-based sample selection (DSS) on top of CSS (ablation)SPCAN w/o DSS · Office-31 (ResNet50)accuracy: 88.1 -> 89.1Improved
add CSS when only DSS is used (ablation)SPCAN w/o CSS · Office-31 (ResNet50)accuracy: 82.4 -> 89.1Improved
apply self-paced sample selection to DANN (ablation)DANN · Office-31 (ResNet50)accuracy: 80.9 -> 86.2Improved
learn block weights lambda_l instead of fixing them to 1/3 (ablation)SPCAN · Office-31 (ResNet50)accuracy: 87.1 -> 89.1Improved
use positive (domain-specific) fixed weights at shallow blocks versus negative (ablation)sSPCAN · Office-31 (ResNet50)accuracy: 85.9 -> 87.1Improved
add collaborative learning with multiple domain classifiers to DANNDANN · Office-31 (ResNet50)accuracy: 80.9 -> 82.4Improved
swap backbone from DANN to SPCAN with VGG19DANN · Office-31 (VGG19)accuracy: 78.4 -> 87.5Improved
swap DANN to SPCAN with DenseNet161 backboneDANN · Office-31 (DenseNet161)accuracy: 82.7 -> 90.1Improved
add collaborative and adversarial scheme to DANN for videoDANN · UCF101-10/HMDB51-10accuracy: 87.7 -> 90.4Improved
add self-paced sample selection to CAN for videoCAN · UCF101-10/HMDB51-10accuracy: 90.4 -> 92.1Improved
exchange pseudo-labeled samples between RGB and flow streamsSPCAN · UCF101-10/HMDB51-10accuracy: 92.1 -> 93.5Improved

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