2 papers
eess.IV2025
A Bayesian Approach to Segmentation with Noisy Labels via Spatially Correlated Distributions
Ryu Tadokoro, Tsukasa Takagi, Shin-ichi Maeda
In semantic segmentation, the accuracy of models heavily depends on the high-quality annotations. However, in many practical scenarios, such as medical imaging and remote sensing,…
eess.IV2023
JPEG Information Regularized Deep Image Prior for Denoising
Tsukasa Takagi, Shinya Ishizaki, Shin-ichi Maeda
Image denoising is a representative image restoration task in computer vision. Recent progress of image denoising from only noisy images has attracted much attention. Deep image pr…