Search Results for author:
Found 9 papers, 6 papers with code
An Image Segmentation Model with Transformed Total Variation
Based on transformed $\ell_1$ regularization, transformed total variation (TTV) has robust image recovery that is competitive with other nonconvex total variation (TV) regularizers, such as TV$^p$, $0<p<1$.
A Proximal Algorithm for Network Slimming
This time-consuming, three-step process is a result of using subgradient descent to train CNNs.
Weighted Anisotropic-Isotropic Total Variation for Poisson Denoising
Poisson noise commonly occurs in images captured by photon-limited imaging systems such as in astronomy and medicine.
Difference of Anisotropic and Isotropic TV for Segmentation under Blur and Poisson Noise
In this paper, we aim to segment an image degraded by blur and Poisson noise.
An Efficient Smoothing and Thresholding Image Segmentation Framework with Weighted Anisotropic-Isotropic Total Variation
In this paper, we design an efficient, multi-stage image segmentation framework that incorporates a weighted difference of anisotropic and isotropic total variation (AITV).
Improving Network Slimming with Nonconvex Regularization
Network slimming with T$\ell_1$ regularization also outperforms the latest Bayesian modification of network slimming in compressing a CNN architecture in terms of memory storage while preserving its model accuracy after channel pruning.
Clustering COVID-19 Lung Scans
While tests do exist for COVID-19, the goal of our research is to explore other methods of identifying infected individuals.
A Weighted Difference of Anisotropic and Isotropic Total Variation for Relaxed Mumford-Shah Color and Multiphase Image Segmentation
In a class of piecewise-constant image segmentation models, we propose to incorporate a weighted difference of anisotropic and isotropic total variation (AITV) to regularize the partition boundaries in an image.
$\ell_0$ Regularized Structured Sparsity Convolutional Neural Networks
Deepening and widening convolutional neural networks (CNNs) significantly increases the number of trainable weight parameters by adding more convolutional layers and feature maps per layer, respectively.
