no code implementations • 6 Feb 2024 • Huajun Xi, Jianguo Huang, Kangdao Liu, Lei Feng, Hongxin Wei
In this work, we empirically show that current confidence calibration methods (e. g., temperature scaling) normally lead to larger prediction sets in adaptive conformal prediction.
1 code implementation • 28 Oct 2023 • Shuoyuan Wang, Jindong Wang, Huajun Xi, Bob Zhang, Lei Zhang, Hongxin Wei
However, the high computational cost of optimization-based TTA algorithms makes it intractable to run on resource-constrained edge devices.
2 code implementations • 10 Oct 2023 • Jianguo Huang, Huajun Xi, Linjun Zhang, Huaxiu Yao, Yue Qiu, Hongxin Wei
Conformal prediction is a statistical framework that generates prediction sets containing ground-truth labels with a desired coverage guarantee.