AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels

Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Jiechao Xiong, Shaogang Gong, Yizhou Wang, Yuan Yao

TPAMI 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 58 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
detect outliers globally with URLR instead of majority voting plus rankSVMsubjective visual property ranking · Image interestingnessKendall tau distanceImproved
jointly learn outlier detection and ranking with features (URLR) instead of featureless Huber-LASSO (ablation)URLR · Image interestingnessKendall tau distanceImproved
prune outliers (URLR) instead of using all annotations (Raw) (ablation)URLR · Image interestingnessKendall tau distanceImproved
use majority voting for outlier pruning instead of using all annotationslearning to rank · Image interestingness (sparse annotation)Kendall tau distanceNo clear effect
increase pruning rate beyond 55% (ablation)URLR · Image interestingnessKendall tau distance: over 55%Hurt
increase pruning rate from low values toward 55% (ablation)URLR · Image interestingnessKendall tau distanceImproved
use URLR instead of Huber-LASSO-FL on densely annotated video datavideo interestingness · Video interestingnessKendall tau distanceNo clear effect
use URLR with added synthetic outliers (Orig+synth)relative attribute prediction · PubFig and Scene classificationclassification accuracyImproved
use URLR instead of Huber-LASSO-FL at 25% error ratioage rank prediction · FG-NET (Unint.+Int.)rank correlation: 301 -> 546 dimensionsImproved
use URLR instead of Huber-LASSO-FL at 10% error ratioage rank prediction · FG-NET (Unint.)rank correlationNo clear effect
use majority voting with 5 comparisons per pair instead of Rawage rank prediction · FG-NET (Unint.+Int.)rank correlationImproved
use URLR instead of Maj-Vot-1 after pruning rate passes 10%age rank prediction · FG-NET (5 comparisons per pair)rank correlation: pruning rate over 10%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