2 code implementations • 15 Nov 2022 • Matteo Rizzo, Cristina Conati, Daesik Jang, Hui Hu
The opacity of deep learning models constrains their debugging and improvement.
1 code implementation • 15 Jun 2021 • Matteo Rizzo, Cristina Conati, Daesik Jang, Hui Hu
We extend this architecture with different models obtained by (i) substituting the TCCNet submodules with C4, the state-of-the-art method for CCC targeting images; (ii) adding a cascading strategy to perform an iterative improvement of the estimate of the illuminant.
6 code implementations • CVPR 2020 • Zili Yi, Qiang Tang, Shekoofeh Azizi, Daesik Jang, Zhan Xu
Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed.
Ranked #6 on Image Inpainting on Places2 val