AI Paper Atlas

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

PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories

Behnam Gholami, Ognjen (Oggi) Rudovic, Vladimir Pavlovic

ICCV 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 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 ILS with PUnDA (probabilistic joint latent space and classifier)unsupervised DA · Office+Caltech10 average, VGG-FC6 featuresaccuracy: 81.3 -> 83.4Improved
replace ILS with PUnDAunsupervised DA · Office+Caltech10 average, VGG-FC7 featuresaccuracy: 79.2 -> 81.7Improved
replace ILS with PUnDAunsupervised DA · Office+Caltech10 average, SURF featuresaccuracy: 46.7 -> 48.8Improved
replace ILS with PUnDAunsupervised DA · Multi-PIE average (source C27)accuracy: 64.2 -> 65.7Improved
replace ILS with PUnDA on small-angle transferunsupervised DA · Multi-PIE C09 (source C27)accuracy: 96.6 -> 94.3Hurt
add domain mismatch regularization term (lambda greater than 0) (ablation)PUnDA · Office+Caltech10, VGG-FC6accuracyImproved
vary lambda' over 0 to 10 (ablation)PUnDA · Office+Caltech10, VGG-FC6accuracyNo clear effect
use unlabeled target data in classifier learning (ablation)PUnDA · Office+Caltech10, VGG-FC6accuracyImproved
use VGG-FC7 instead of VGG-FC6 featuresPUnDA · Office+Caltech10 averageaccuracy: 83.4 -> 81.7Hurt

Later papers that compared with this method

1 later accepted paper reports PU-NDA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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