Within the domain of low-level vision,enhancing low-light images and removing sand-dust from single images are both critical tasks.These challenges are particularly pronounced in real-world applications such as autono...Within the domain of low-level vision,enhancing low-light images and removing sand-dust from single images are both critical tasks.These challenges are particularly pronounced in real-world applications such as autonomous driving,surveillance systems,and remote sensing,where adverse lighting and environmental conditions often degrade image quality.Various neural network models,including MLPs,CNNs,GANs,and Transformers,have been proposed to tackle these challenges,with the Vision KAN models showing particular promise.However,existing models,including the Vision KAN models use deterministic neural networks that do not address the uncertainties inherent in these processes.To overcome this,we introduce the Uncertainty-Aware Kolmogorov-Arnold Network(UAKAN),a novel structure that integrates KAN with uncertainty estimation.Our approach uniquely employs Tokenized KANs for sampling within a U-Net architecture’s encoder and decoder layers,enhancing the network’s ability to learn complex representations.Furthermore,for aleatoric uncertainty,we propose an uncertainty coupling certainty module that couples uncertainty distribution learning and residual learning in a feature fusion manner.For epistemic uncertainty,we propose a feature selection mechanism for spatial and pixel dimension uncertainty modeling,which captures and models uncertainty by learning the uncertainty contained between feature maps.Notably,our uncertainty-aware framework enables the model to produce both high-quality enhanced images and reliable uncertainty maps,which are crucial for downstream applications requiring confidence estimation.Through comparative and ablation studies on our synthetic SLLIE6K dataset,designed for low-light enhancement and sand-dust removal,we validate the effectiveness and theoretical robustness of our methodology.展开更多
This paper examines how the difference in institutional environments constitutes differential IPO underpricing across countries. Using the Heritage Foundation＇s Index of Economic Freedom （IEF） as a proxy for the he...This paper examines how the difference in institutional environments constitutes differential IPO underpricing across countries. Using the Heritage Foundation＇s Index of Economic Freedom （IEF） as a proxy for the heterogeneous institutional environment, and a sample of 3728 IPOs from 22 countries and regions over the period 1993--2014, we find that countries with higher economic freedom have significantly less serious IPO underpricing problems. Moreover, we find that among the 10 economic freedom factors covered by theIEF, financial freedom related factors play a more important role in reducing the IPO underpricing problem. Finally, consistent with the market sentiment hypothesis, we find strong evidence that pre-IPO market sentiment influences IPO firstday returns, and that the IPO underpricing problem is less severe when the market is bearish.展开更多
基金supported by National Key R&D Program of China(2023YFB2504400).
文摘Within the domain of low-level vision,enhancing low-light images and removing sand-dust from single images are both critical tasks.These challenges are particularly pronounced in real-world applications such as autonomous driving,surveillance systems,and remote sensing,where adverse lighting and environmental conditions often degrade image quality.Various neural network models,including MLPs,CNNs,GANs,and Transformers,have been proposed to tackle these challenges,with the Vision KAN models showing particular promise.However,existing models,including the Vision KAN models use deterministic neural networks that do not address the uncertainties inherent in these processes.To overcome this,we introduce the Uncertainty-Aware Kolmogorov-Arnold Network(UAKAN),a novel structure that integrates KAN with uncertainty estimation.Our approach uniquely employs Tokenized KANs for sampling within a U-Net architecture’s encoder and decoder layers,enhancing the network’s ability to learn complex representations.Furthermore,for aleatoric uncertainty,we propose an uncertainty coupling certainty module that couples uncertainty distribution learning and residual learning in a feature fusion manner.For epistemic uncertainty,we propose a feature selection mechanism for spatial and pixel dimension uncertainty modeling,which captures and models uncertainty by learning the uncertainty contained between feature maps.Notably,our uncertainty-aware framework enables the model to produce both high-quality enhanced images and reliable uncertainty maps,which are crucial for downstream applications requiring confidence estimation.Through comparative and ablation studies on our synthetic SLLIE6K dataset,designed for low-light enhancement and sand-dust removal,we validate the effectiveness and theoretical robustness of our methodology.
文摘This paper examines how the difference in institutional environments constitutes differential IPO underpricing across countries. Using the Heritage Foundation＇s Index of Economic Freedom （IEF） as a proxy for the heterogeneous institutional environment, and a sample of 3728 IPOs from 22 countries and regions over the period 1993--2014, we find that countries with higher economic freedom have significantly less serious IPO underpricing problems. Moreover, we find that among the 10 economic freedom factors covered by theIEF, financial freedom related factors play a more important role in reducing the IPO underpricing problem. Finally, consistent with the market sentiment hypothesis, we find strong evidence that pre-IPO market sentiment influences IPO firstday returns, and that the IPO underpricing problem is less severe when the market is bearish.
