Quality Issue
Research on quality issues spans diverse fields, focusing on developing methods to objectively assess and improve the quality of data, models, and processes. Current efforts concentrate on refining evaluation metrics, leveraging machine learning models (like transformers and diffusion models) for quality prediction and enhancement, and designing algorithms to optimize for quality while managing computational constraints. These advancements are crucial for improving the reliability and trustworthiness of AI systems across various applications, from medical diagnosis and financial reporting to language processing and image analysis, ultimately leading to more robust and impactful technologies.
Papers
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk
Quantity over Quality: Training an AV Motion Planner with Large Scale Commodity Vision Data
Lukas Platinsky, Tayyab Naseer, Hui Chen, Ben Haines, Haoyue Zhu, Hugo Grimmett, Luca Del Pero
Quality or Quantity: Toward a Unified Approach for Multi-organ Segmentation in Body CT
Fakrul Islam Tushar, Husam Nujaim, Wanyi Fu, Ehsan Abadi, Maciej A. Mazurowski, Ehsan Samei, William P. Segars, Joseph Y. Lo