AI Paper Atlas

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

Learning by Transferring from Unsupervised Universal Sources

Yu-Xiong Wang, Martial Hebert

AAAI 2016 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 16 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
use unsupervised universal sources instead of naive clustering sources (ablation)MT-SVM · Office Webcam Subset Aaccuracy (%): 67.13 -> 74.83Improved
use unsupervised universal sources instead of naive clustering sources (ablation)MT-SVM · Office Webcam Subset Baccuracy (%): 64.92 -> 74.19Improved
use unsupervised universal sources instead of supervised category sources (ablation)MT-SVM · Office Webcam Subset Baccuracy (%): 70.30 -> 74.19Improved
add transfer from UUS vs target-only SVM (ablation)MT-SVM · Office Webcam Subset Baccuracy (%): 63.34 -> 74.19Improved
increase gamma weight (m) from 0 to 0.7 in elastic net (ablation)MT-SVM · SUN-397 one-shotaccuracy (%): 10.51 -> 15.54Improved
increase m from 0.7 to 0.9 (ablation)MT-SVM · SUN-397 one-shotaccuracy (%): 15.54 -> 15.23No clear effect
generate UUS on PASCAL 2007 region proposals instead of ILSVRC (ablation)MT-SVM · SUN-397accuracy (%)Improved
elastic net MT-SVM instead of l2-only (EE-SVM) or l1-only (Multi-KT) transfer weightsMT-SVM · SUN-397accuracy (%)Improved
elastic net MT-SVM instead of l2+l0 GreedyTLMT-SVM · SUN-397accuracy (%)Improved

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