PecMan is a fairness-aware human-AI cooperative classification framework for medical images that jointly handles subgroup reliability, decision allocation to AI or humans, and collaborative predictions, introducing the FairHAI benchmark and showing better trade-offs than separate approaches.
Do humans and machines have the same eyes? human- machine perceptual differences on image classification
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.
citing papers explorer
-
People-Centred Medical Image Analysis via Fairness-Aware Human-AI Cooperation
PecMan is a fairness-aware human-AI cooperative classification framework for medical images that jointly handles subgroup reliability, decision allocation to AI or humans, and collaborative predictions, introducing the FairHAI benchmark and showing better trade-offs than separate approaches.
-
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.