AI Paper Atlas

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

Attention Bridging Network for Knowledge Transfer

Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 28 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 source-domain data with classification loss only (ablation)Grad-CAM baseline · VOC 2012 val (direct attention-map evaluation)mIoU: 30.2 -> 31.7No clear effect
add attention constraint loss with fine-tuning (ablation)Grad-CAM + source data · VOC 2012 val (direct attention-map evaluation)mIoU: 31.7 -> 39.4Improved
use joint two-domain training with weight sharing instead of fine-tuning (ablation)attention constraint model · VOC 2012 val (direct attention-map evaluation)mIoU: 39.4 -> 46.2Improved
add adversary training loss (ablation)joint training with attention constraint · VOC 2012 val (direct attention-map evaluation)mIoU: 46.2 -> 50.9Improved
add adversary training loss (ablation)joint training with attention constraint · VOC 2012 test (direct attention-map evaluation)mIoU: 47.5 -> 51.2Improved
increase source domain data from 2K to 20K images (ablation)AttnBN · VOC 2012 val (direct attention-map evaluation)mIoU: 45.1 -> 50.9Improved
use only 10% source data (about 2K images) (ablation)AttnBN vs Grad-CAM · VOC 2012 val (direct attention-map evaluation)mIoU: 14.9%Improved
use AttnBN attention maps as foreground cuesDSRG · VOC 2012 val (weakly-supervised segmentation)mIoU: 59.0 -> 62.1Improved
use AttnBN attention maps as foreground cuesDSRG · VOC 2012 test (weakly-supervised segmentation)mIoU: 60.4 -> 63.0Improved
add attention constraint loss for domain generalization (ablation)Ls-cl classifier · Single-label to multi-label domainmAP: 61.3 -> 66.7Improved
add attention constraint loss to adversarial adaptation (ablation)Ls-cl + Ladv · Single-label to multi-label domainmAP: 64.5 -> 71.0Improved
add attention constraint loss for generalization (ablation)Ls-cl classifier · Caltech-101 to VOC 2007accuracy: 0.62 -> 0.71Improved

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