1 code implementation • 12 Dec 2023 • Mingjian Zhu, Hanting Chen, Mouxiao Huang, Wei Li, Hailin Hu, Jie Hu, Yunhe Wang
The misuse of AI imagery can have harmful societal effects, prompting the creation of detectors to combat issues like the spread of fake news.
no code implementations • 18 Sep 2023 • Mouxiao Huang
These scenarios often feature low-quality face images, necessitating the modeling of data uncertainty to improve stability under extreme conditions.
no code implementations • 15 Feb 2023 • Mouxiao Huang, Yu Qiao
However, neural networks often suffer from the overconfidence issue, making high confidence for OOD data which are never seen during training process and may be irrelevant to training data, namely in-distribution (ID) data.
no code implementations • 2 Dec 2022 • Lei Shang, Mouxiao Huang, Wu Shi, Yuchen Liu, Yang Liu, Fei Wang, Baigui Sun, Xuansong Xie, Yu Qiao
Intuitively, FR algorithms can benefit from both the estimation of uncertainty and the detection of out-of-distribution (OOD) samples.