We present a novel method for inferring ground-truth signal from multiple degraded signals, affected by different amounts of sensor exposure. The algorithm learns a multiplicative degradation effect by performing iterative corrections of two signals solely from the ratio between them. The degradation function d should be continuous, satisfy monotonicity, and d(0) = 1. We use smoothed monotonic regression method, where we easily incorporate the aforementioned criteria to the fitting part. We include theoretical analysis and prove convergence to the ground-truth signal for the noiseless measurement model. Lastly, we present an approach to fuse the noisy corrected signals using Gaussian processes. We use sparse Gaussian processes that can be utilized for a large number of measurements together with a specialized kernel that enables the estimation of noise values of all sensors. The data fusion framework naturally handles data gaps and provides a simple and powerful method for observing the signal trends on multiple timescales(long-term and short-term signal properties). The viability of correction method is evaluated on a synthetic dataset with known ground-truth signal.
提出了一种多波段遥感图像的贝叶斯融合方法。所观察到的图像与要通过物理退化恢复的高光谱和高空间分辨率图像相关，由传感器特性定义的空间和光谱模糊和/或子采样。在贝叶斯估计框架内制定的融合问题。一个适当的先验分布，利用几何考虑。为了从感兴趣场景的后验分布计算其贝叶斯估计，设计了马尔可夫链蒙特卡罗算法来根据目标分布生成渐近分布的样本。为了有效地从这种高维分布中采样，在Gibbs采样策略中引入了Hamilton Monte Carlo步骤。相对于几个国家的最先进的融合技术，所提出的融合方法的效率进行评估。特别地，低空间分辨率的高光谱和多光谱图像被融合以产生高空间分辨率的高光谱图像。
Institute of Imaging and Computer Vision, RWTH Aachen University（亚琛工业大学成像与计算机视觉研究所）
Recent developments in fluorescence microscopy allow capturing high-resolution 3D images over time for living model organisms. To be able to image even large specimens, techniques like multi-view light-sheet imaging record different orientations at each time point that can then be fused into a single high-quality volume. Based on measured point spread functions (PSF), deconvolution and content fusion are able to largely revert the inevitable degradation occurring during the imaging process. Classical multi-view deconvolution and fusion methods mainly use iterative procedures and content-based …
The spatial and spectral degradation functions are critical to hyper- and multi-spectral image fusion. However, few work has been payed on the estimation of the degradation functions. To learn the spatial response function and the point spread function from the image pairs to be fused, we propose a Dirichlet network, where both functions are properly constrained. Specifically, the spatial response function is constrained with positivity, while the Dirichlet distribution along with a total variation is imposed on the point spread function. To the best of our knowledge, the neural netwrok and th…
Non-Iterative Knowledge Fusion in Deep Convolutional Neural Networks
S.P. Kapitsa Research Institute of Technology (Technological Research Institute) of Ulyanovsk State University（乌里扬诺夫斯克国立大学S.P.卡皮察技术研究所（技术研究所））；Ulyanovsk State Technical University（乌里扬诺夫斯克国立技术大学）；Kotel’nikov Institute of Radio Engineering and Electronics of Russian Academy of Sciences (Ulyanovsk branch)（俄罗斯科学院科捷利尼科夫无线电工程与电子研究所（乌里扬诺夫斯克分支））
Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox
Department of Analytics and Information Systems（分析与信息系统系）；University of San Francisco（旧金山大学）；Department of Applied AI and Industry Innovation（应用人工智能与产业创新系）；Vector Institute for Artificial Intelligence（人工智能研究院）；Department of Management Science and Information Systems（管理科学与信息系统系）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）
National Institute of Health Data Science, Peking University（北京大学健康医疗大数据国家研究院）；Institute of Medical Technology, Health Science Center of Peking University（北京大学医学部医学技术研究院）
Unsupervised/self-supervised time series representation learning is a challenging problem because of its complex dynamics and sparse annotations. Existing works mainly adopt the framework of contrastive learning with the time-based augmentation techniques to sample positives and negatives for contrastive training. Nevertheless, they mostly use segment-level augmentation derived from time slicing, which may bring about sampling bias and incorrect optimization with false negatives due to the loss of global context. Besides, they all pay no attention to incorporate the spectral information in fea…
Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach introduces nontrivial training time overhead due to the lack of data locality and computation parallelism. In this work, we propose to fuse the optimizer with forward or backward computation to better leverage locality and parallelism during training. By reordering the forward computation, gradient calculation, and parameter updating, our proposed method improves the efficiency…
Cross-Fusion Distance: A Novel Metric for Measuring Fusion and Separability Between Data Groups in Representation Space
CEDAR, Knight Cancer Institute, Oregon Health and Science University, OR, USA（CEDAR、骑士癌症研究所、俄勒冈健康与科学大学，俄勒冈州，美国）；Brenden-Colson Center for Pancreatic Care, Oregon Health and Science University, OR, USA（布伦登-科尔森胰腺护理中心、俄勒冈健康与科学大学，俄勒冈州，美国）
National Chung Hsing University（中兴大学）；National Taichung University of Science and Technology（台中科技大学）
Image restoration is a challenging and ill-posed problem which also has been a long-standing issue. However, most of learning based restoration methods are proposed to target one degradation type which means they are lack of generalization. In this paper, we proposed a multi-branch restoration model inspired from the Human Visual System (i.e., Retinal Ganglion Cells) which can achieve multiple restoration tasks in a general framework. The experiments show that the proposed multi-branch architecture, called CMFNet, has competitive performance results on four datasets, including image dehazing, …
