no code implementations • ICCV 2023 • SoonCheol Noh, DongEon Jeong, Jee-Hyong Lee
Deep learning models need to detect out-of-distribution (OOD) data in the inference stage because they are trained to estimate the train distribution and infer the data sampled from the distribution.
no code implementations • CVPR 2022 • Noo-ri Kim, Jee-Hyong Lee
The proposed methods show 70. 9%, 30. 3%, and 78. 9% accuracy on CIFAR-10, CIFAR-100, SVHN dataset with just one labeled sample per class, which are improved by 8. 9% to 120. 2% compared to the existing approaches.
no code implementations • 8 Sep 2015 • Yeounoh Chung, Chang-yong Park, Noo-ri Kim, Hana Cho, Taebok Yoon, Hunjoo Lee, Jee-Hyong Lee
Then, it develops a local bot detection model for each player group.