1 code implementation • 29 Aug 2023 • Yiming Huang, Guole Liu, Yaoru Luo, Ge Yang
We then apply differentiable top-k feature adaptation to train the patch descriptor, mapping the extracted feature representations to a new vector space, enabling effective detection of anomalies.
1 code implementation • 30 Apr 2022 • Yaoru Luo, Guole Liu, Yuanhao Guo, Ge Yang
Our understanding of the learning behavior of DNNs trained by noisy segmentation labels remains limited.
no code implementations • 22 Mar 2021 • Yaoru Luo, Guole Liu, Yuanhao Guo, Ge Yang
When trained with these noisy labels, DNNs provide largely the same segmentation performance as trained by the original ground truth.