Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Park, Fredrick"'
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
Externí odkaz:
http://arxiv.org/abs/2406.00571
As a popular channel pruning method for convolutional neural networks (CNNs), network slimming (NS) has a three-stage process: (1) it trains a CNN with $\ell_1$ regularization applied to the scaling factors of the batch normalization layers; (2) it r
Externí odkaz:
http://arxiv.org/abs/2307.00684
Poisson noise commonly occurs in images captured by photon-limited imaging systems such as in astronomy and medicine. As the distribution of Poisson noise depends on the pixel intensity value, noise levels vary from pixels to pixels. Hence, denoising
Externí odkaz:
http://arxiv.org/abs/2307.00439
In this paper, we aim to segment an image degraded by blur and Poisson noise. We adopt a smoothing-and-thresholding (SaT) segmentation framework that finds a piecewise-smooth solution, followed by $k$-means clustering to segment the image. Specifical
Externí odkaz:
http://arxiv.org/abs/2301.03393
In this paper, we design an efficient, multi-stage image segmentation framework that incorporates a weighted difference of anisotropic and isotropic total variation (AITV). The segmentation framework generally consists of two stages: smoothing and th
Externí odkaz:
http://arxiv.org/abs/2202.10115
Convolutional neural networks (CNNs) have developed to become powerful models for various computer vision tasks ranging from object detection to semantic segmentation. However, most of the state-of-the-art CNNs cannot be deployed directly on edge dev
Externí odkaz:
http://arxiv.org/abs/2010.01242
With the ongoing COVID-19 pandemic, understanding the characteristics of the virus has become an important and challenging task in the scientific community. While tests do exist for COVID-19, the goal of our research is to explore other methods of id
Externí odkaz:
http://arxiv.org/abs/2009.09899
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. In particular, we replace the total va
Externí odkaz:
http://arxiv.org/abs/2005.04401
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. By imposing inter- and intra-group sparsity on
Externí odkaz:
http://arxiv.org/abs/1912.07868
Publikováno v:
Communications on Applied Mathematics and Computation; June 2024, Vol. 6 Issue: 2 p1369-1405, 37p