Evaluating AI systems under uncertain ground truth: a case study in dermatology.
David StutzAli Taylan CemgilAbhijit Guha RoyTatiana MatejovicovaMelih BarsbeyPatricia StrachanMike SchaekermannJan FreybergRajeev RikhyeBeverly FreemanJavier Perez MatosUmesh TelangDale R. WebsterYuan LiuGregory S. CorradoYossi MatiasPushmeet KohliYun LiuArnaud DoucetAlan KarthikesalingamPublished in: CoRR (2023)
Keyphrases
- ai systems
- ground truth
- artificial intelligence
- intelligent systems
- natural language generation
- ground truth data
- case study
- general intelligence
- high quality
- game play
- decision making
- gold standard
- manually labeled
- expert systems
- point to point correspondences
- image segmentation
- domain knowledge
- object oriented
- information retrieval
- hybrid intelligent systems