Get Started
Home
Topics
Search
Library
Research questionHow can subjective image-quality assessments resist adversarial ratings that distort mean opinion scores?Standard outlier tests may appear effective against random or typical unreliable ratings while remaining vulnerable to rating patterns deliberately chosen to bias the mean opinion score. The difficulty is identifying such worst-case patterns and assessing whether outlier handling still recovers the underlying quality judgment.
Computer Vision
Evaluation & Benchmarks
Image & Video Processing
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Adversarial Stress Testing of Outlier Detection in Subjective Image Quality AssessmentThe evidence concerns subjective assessments using discrete absolute-category ratings and continuous visual-analog-scale ratings. It evaluates hard and soft outlier-detection methods with optimized adversarial attack generators and reports empirical worst-case reconstruction performance; the findings do not establish behavior beyond the tested assessment formats and experiments.research paper · Sep 2, 2026
Related questions
How can object detectors produce trustworthy confidence scores in degraded or ambiguous scenes?How can quality assessment detect and localize anomalies introduced by enhancement in real-world user-generated images?How can image-poisoning attacks remain effective across supervised and self-supervised learning without obvious visual artifacts?How can subjective-label models remain calibrated across legitimate differences in human values?