AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Testing Using Privileged Information by Adapting Features With Statistical Dependence

Kwang In Kim, James Tompkin

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 0 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 TUPI denoising with other feature sets as test time informationinitial predictor · MFeat (F1 as baseline features)ranking accuracy (%): 77.85 -> 81.97Improved
add TUPI denoising with other feature sets as test time informationinitial predictor · MFeat (F4 as baseline features)ranking accuracy (%): 70.88 -> 74.33Improved
add TUPI denoising with other feature sets as test time informationinitial predictor · MFeat (F6 as baseline features)ranking accuracy (%): 77.10 -> 82.25Improved
add 10 random features to the test time information (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 81.97 -> 82.14No clear effect
add 10 random features to the test time information (ablation)TUPI · MFeat (F5 as baseline features)ranking accuracy (%): 78.19 -> 78.05No clear effect
use only 1 of 5 feature sets instead of all 5 (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 81.97 -> 79.88Hurt
use only 3 of 5 feature sets instead of all 5 (ablation)TUPI · MFeat (F6 as baseline features)ranking accuracy (%): 82.25 -> 80.71Hurt
use only 3 of 5 feature sets instead of all 5 (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 81.97 -> 82.15No clear effect
supply noise-free ground-truth targets as test time features (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 77.85 -> 99.56Improved
increase noise std of ground-truth test time features from 0.2 to 1 (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 87.84 -> 78.84Hurt
add copies of the initial prediction to the test time features (11 copies) (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 81.97 -> 78.96Hurt
add a single copy of the initial prediction to the test time features (ablation)TUPI · MFeat (F1 as baseline features)ranking accuracy (%): 81.97 -> 82.81No clear effect

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