AI Paper Atlas

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

Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond

Piotr Koniusz, Yusuf Tas, Hongguang Zhang, Mehrtash Harandi, Fatih Porikli, Rui Zhang

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 48 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
replace Euclidean alignment with JBLD distance (ablation)So-HoT supervised domain adaptation · Open MIC combined settop-1 accuracy (%): 62.8 -> 64.2Improved
add target-stream fine-tuning with JBLD alignment versus S+TVGG16 two-stream · Open MIC combined settop-1 accuracy (%): 55.9 -> 64.2Improved
replace Euclidean alignment with JBLD distance (ablation)So-HoT · Office AD, VGG16accuracy (%): 89.45 -> 90.80Improved
replace Euclidean alignment with AIRM distance (ablation)So-HoT · Office AD, VGG16accuracy (%): 89.45 -> 90.72Improved
replace Euclidean alignment with JBLD distance (ablation)So-HoT · Open MIC Clk subsetaccuracy (%): 59.3 -> 61.2Improved
use AIRM instead of JBLD distance (ablation)So-HoT · Open MIC Clk subsetaccuracy (%): 61.2 vs 61.1No clear effect
switch backbone from VGG16 to GoogLeNet (ablation)two-stream JBLD · Office ADaccuracy (%): 90.80 -> 91.33Improved
add source data to target-only fine-tuning (S+T vs T)VGG16 · Open MIC combined settop-1 accuracy (%): 56.5 -> 55.9Hurt
project features with Nystrom projections before non-Euclidean distance (ablation)JBLD/AIRM alignment · training timespeed: 210x faster than naive non-Euclidean distancesImproved
add JBLD domain adaptation on top of S+TVGG16 · Open MIC subset Shxtop-1 accuracy (%): 29.0 -> 48.5Improved
add JBLD domain adaptation over source-only (S)VGG16 · Open MIC subset Glstop-1 accuracy (%): 15.8 -> 74.4Improved
replace Euclidean alignment with JBLD distance (ablation)So-HoT · Office-Home Cl->Araccuracy (%): 48.1 -> 49.2Improved

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