AI Paper Atlas

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

Asking Friendly Strangers: Non-Semantic Attribute Transfer

Nils Murrugarra-Llerena, Adriana Kovashka

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 4 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 learned attention weights with uniform weights (multi-domain, DD) (ablation)ATTENTION-DD · overall averageF-measure: 0.67 -> 0.08Hurt
replace learned attention weights with uniform weights (all domains, AD) (ablation)ATTENTION-AD · overall averageF-measure: 0.67 -> 0.17Hurt
replace learned attention weights with uniform weights (single domain) (ablation)ATTENTION-SD · overall averageaccuracy: 0.92 -> 0.80Hurt
add non-semantic transfer from other domains (DD) over target-onlyTARGET-ONLY · overall averageF-measure: 0.62 -> 0.67Improved
add non-semantic transfer from other domains (DD) over target-onlyTARGET-ONLY · texturesF-measure: 0.68 -> 0.96Improved
add non-semantic transfer from other domains (DD) over target-onlyTARGET-ONLY · objectsF-measure: 0.50 -> 0.47Hurt
add non-semantic transfer from other domains (DD) over target-onlyTARGET-ONLY · overall averageaccuracy: 0.91 -> 0.94Improved
transfer from all domains including target domain (AD) instead of other domains only (DD)ATTENTION-DD · overall averageF-measure: 0.67 -> 0.67No clear effect
attention transfer vs Tzeng et al. domain confusion (DD)CONFUSION-DD · overall averageF-measure: 0.63 -> 0.67Improved
attention transfer vs Tzeng et al. domain confusion (DD)CONFUSION-DD · overall averageaccuracy: 0.94 -> 0.94No clear effect
attention transfer vs standard fine-tuning (AD)FINETUNE-AD · overall averageF-measure: 0.39 -> 0.67Improved
ensemble ATTENTION-SD with TARGET-ONLYATTENTION-SD · overall averageF-measure: 0.62 -> 0.64Improved

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