Generates high-resolution images from low-resolution inputs.
problem Generating realistic images from low-resolution inputs.
method Latent Adversarial Generator (LAG) using perceptual loss.
result Samples of high-resolution images from low-resolution inputs.
MeshfreeFlowNet generates high-resolution spatio-temporal solutions from low-resolution inputs.
problem Generating high-resolution spatio-temporal solutions from low-resolution inputs.
method Physics-constrained deep learning framework using fully convolutional encoders.
result Significantly outperforms existing baselines in super-resolution of turbulent flows.
Study on VC dimension of GCNNs with input resolution effects.
problem Understanding the generalization capabilities of GCNNs.
method Derived upper and lower bounds for VC dimension, analyzed factors affecting it.
result Extended previous results on VC dimension of GCNNs, providing insights into input resolution dependence.
Physics-informed neural operator learns from coarse to fine discretized data.
problem Lack of high-fidelity training data and uneven grid resolution.
method Physics-informed multi-resolution neural operator framework.
result Learn from arbitrarily discretized input functions using latent embedding and finite difference solver.
Generative adversarial networks generate realistic, time-evolving high-resolution atmospheric fields.
problem Improving spatial resolution of low-resolution atmospheric images.
method Recurrent, stochastic super-resolution GAN for generating ensembles of time-evolving high-resolution atmospheric fields.
result The GAN produces realistic, temporally consistent super-resolution sequences for radar-measured precipitation and cloud optical thickness.
RI-DeepONet learns neural operators from arbitrary sensor data.
problem Discretization of input functions limits practical applications of DeepONet.
method Introduces RI-DeepONet and two dictionary learning algorithms for INRs.
result RINO handles arbitrary sensor data robustly and applies to various problems.
Paper proposes combining GAM and DNN for accurate peak demand estimation from lower-resolution data.
problem Predicting high-resolution peak demand from limited lower-resolution data.
method Combines generalized additive models (GAM) and deep neural networks (DNN) for half-hourly load forecasting.
result Proposed method reduces out-of-sample RMSE by 57.4% compared to benchmark.
A method to analyze neural network performance by measuring layer saturation.
problem Understanding which layers contribute to network performance.
method Layer saturation method: restricts layer output to eigenspace of variance matrix.
result Layer saturation indicates which layers contribute to network performance.
KOLMOGOROV-OPTIMAL RESOLUTION ESTIMATION (KORE) solves spline regression without exhaustive search
problem Hyperparameter tuning in spline regression
method Solving for optimal resolution analytically
result KORE matches exhaustive cross-validation and outperforms tuned models
Generative deep learning improves precipitation forecasts by adding resolution.
problem Inaccurate and unreliable precipitation forecasts due to unresolved processes.
method Applying GANs to super-resolve low-resolution weather model data using radar measurements.
result GANs and VAE-GANs produce high-resolution precipitation maps with better statistical properties than existing methods.
This study prioritizes temporal resolution over spatial in energy systems models due to higher influence.
problem The impact of spatial and temporal resolution on energy system models.
method Global sensitivity analysis to compare structural aspects, spatial, and temporal resolution.
result Temporal resolution has a higher influence on all results parameters compared to spatial resolution.
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolu…
Running high-resolution physical models is computationally expensive and essential for many disciplines. Agriculture, transportation, and energy are sectors that depend on high-resolution weather models, which typically consume many hours of large High Performance Computing (HPC) systems to deliver timely results. Many…
Study shows zero-shot super-resolution in neural operators is impossible in many cases.
problem Understanding the theoretical limits of zero-shot super-resolution in neural operators.
method Systematic theoretical study including information-theoretic and generalization bounds analysis.
result Zero-shot super-resolution is information-theoretically impossible in many settings.
Study uses CNNs to upscale wind speed data from 100 km to 3 km, improving subgrid-scale variability.
problem Recovering fine-scale wind speed information from coarse data.
method Convolutional neural networks (CNNs) with different input configurations (coarse wind speed, fine-scale topography, diurnal cycle) were tested.
result CNN models with coarse wind and fine topography inputs perform best in generalizing to unseen regions.
SRFRN accelerates image super-resolution using shallow residual units.
problem High computational complexity and time in deep learning image super-resolution.
method SRFRN uses a bicubic interpolated low-resolution image and residual representative units (RFR) for faster and more efficient high-resolution image reconstruction.
result SRFRN achieves superior performance and faster execution time compared to existing methods.
New deep learning method improves 4D Flow MRI super-resolution under domain shift.
problem Domain shift in low-resolution 4D Flow MRI data.
method Distributional deep learning framework for domain generalization.
result Framework significantly outperforms traditional methods in real data applications.
Bayesian image reconstruction using pre-trained generative models.
problem Distribution shifts and latent variable changes in image data.
method Combining SOTA generative models with Bayes' theorem for image restoration tasks.
result Competitive performance on super-resolution and in-painting tasks without training.
HRFA generates high-resolution, realistic adversarial examples for DNNs.
problem Revealing vulnerabilities of DNNs with imperceptible, semantic attacks.
method Modifies latent feature representation, backpropagating through generative model.
result Generates adversarial examples with up to 1024x1024 resolution, evading denoising defenses.
In this paper we propose a generalization of deep neural networks called deep function machines (DFMs). DFMs act on vector spaces of arbitrary (possibly infinite) dimension and we show that a family of DFMs are invariant to the dimension of input data; that is, the parameterization of the model does not directly hinge …
CascadeXML improves multi-resolution learning for XMC with transformer features.
problem Learning subset labels from millions of choices with trade-offs between performance and computation.
method End-to-end multi-resolution learning pipeline using transformer multi-layer architecture.
result Significantly outperforms existing approaches on benchmark datasets.
MetNet forecasts precipitation up to 8 hours with high spatial and temporal resolution.
problem Precise weather forecasting for long lead times.
method Neural network architecture using axial self-attention for global context aggregation.
result MetNet outperforms Numerical Weather Prediction at forecasts of up to 8 hours.
Paper proposes SMFN for high-res spherical video super-resolution.
problem Super-resolution of 360-degree panoramic videos is expensive and challenging.
method Deformable convolutions, mixed attention mechanism, dual learning strategy, weighted mean square error loss function.
result The proposed SMFN method improves super-resolution of equatorial regions in 360-degree videos.
Visualizing an outfit is an essential part of shopping for clothes. Due to the combinatorial aspect of combining fashion articles, the available images are limited to a pre-determined set of outfits. In this paper, we broaden these visualizations by generating high-resolution images of fashion models wearing a custom o…
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the …
Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and processes only a fraction of the full resolution input image. The locations to p…
Over the past decade, many Super Resolution techniques have been developed using deep learning. Among those, generative adversarial networks (GAN) and very deep convolutional networks (VDSR) have shown promising results in terms of HR image quality and computational speed. In this paper, we propose two approaches based…
This paper develops a new deep neural network optimized equalization framework for massive multiple input multiple output orthogonal frequency division multiplexing (MIMOOFDM) systems that employ low-resolution analog-to-digital converters (ADCs) at the base station (BS). The use of lowresolution ADCs could largely red…
Enhances VAEs for sharper image synthesis.
problem Blurriness in generated images from VAEs.
method Integrates a downscaled version of the original image into the VAE framework and uses it as input to the decoder.
result Improves FID score in image synthesis while maintaining similar log-likelihood performance.
Random feature model approximates PDE solutions efficiently.
problem Approximating solutions to PDEs with high-dimensional inputs and outputs.
method Random feature model applied to infinite-dimensional operators.
result Efficient and accurate approximation of PDE solutions.
Image classification with deep neural networks is typically restricted to images of small dimensionality such as 224 x 244 in Resnet models [24]. This limitation excludes the 4000 x 3000 dimensional images that are taken by modern smartphone cameras and smart devices. In this work, we aim to mitigate the prohibitive in…
With super-resolution optical microscopy, it is now possible to observe molecular interactions in living cells. The obtained images have a very high spatial precision but their overall quality can vary a lot depending on the structure of interest and the imaging parameters. Moreover, evaluating this quality is often di…
This thesis investigates unsupervised time series representation learning for sequence prediction problems, i.e. generating nice-looking input samples given a previous history, for high dimensional input sequences by decoupling the static input representation from the recurrent sequence representation. We introduce thr…
Computed tomography (CT) is widely used in screening, diagnosis, and image-guided therapy for both clinical and research purposes. Since CT involves ionizing radiation, an overarching thrust of related technical research is development of novel methods enabling ultrahigh quality imaging with fine structural details whi…
Improved electrical load forecasting model using Fourier-enhanced RNN.
problem Electrical load time series downscaling with high accuracy and low error.
method Combines recurrent neural network with Fourier seasonal embeddings and self-attention.
result Significantly reduces RMSE across different time horizons compared to existing methods.
WavPool improves deep neural networks with wavelet-based pooling.
problem Improving efficiency and performance of deep neural networks.
method Introducing WavPool, a wavelet-transform-based pooling layer.
result WavPool outperforms existing network architectures by 10% on CIFAR-10.
Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly…
This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To re…
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network ba…
LSTM model predicts rainfall runoff with high temporal resolution.
problem Accurate and efficient rainfall runoff simulations for flood risk management.
method Data-driven rainfall runoff model using Long-short-Term-Memory (LSTM) networks.
result LSTM model achieves high-resolution discharge predictions with improved performance.
Proposes a new method to learn operators for stochastic problems using DeepONet with autoencoder.
problem Efficiently solve forward and inverse stochastic problems with limited data.
method MultiAuto-DeepONet, a multi-resolution autoencoder DeepONet model.
result The model effectively handles high-dimensional stochastic inputs and reduces the number of trainable parameters.
Deep learning improves stochastic downscaling of climate variables.
problem Accurately capturing climatic variability at local scales.
method Proposed improvements to GANs for stochastic downscaling of climate variables.
result Improved stochastic calibration of GANs for high-resolution climate predictions.
Generative model downgrades coarse satellite images to fine resolution.
problem Reconstructing fine resolution satellite images from coarse scale inputs.
method Combines U-Net transfer encoder with diffusion-based generative model.
result Excellent performance (R2 = 0.65 to 0.94) across seasonal regional splits.
XR-Transformer accelerates XMC by recursively fine-tuning on multi-resolution objectives.
problem Efficiently classifying texts with large label sets.
method Recursive multi-resolution fine-tuning of transformers.
result XR-Transformer achieves 20x faster training time and 54% Precision@1 on Amazon-3M.
A new autoencoder architecture captures multiscale data.
problem Multiscale spatio-temporal data representation.
method Integrates multigrid methods, convolutional autoencoders, and transfer learning.
result Adaptive, hierarchical architecture captures different scaled features dynamically.
Methods for learning feature representations for Offline Handwritten Signature Verification have been successfully proposed in recent literature, using Deep Convolutional Neural Networks to learn representations from signature pixels. Such methods reported large performance improvements compared to handcrafted feature …
NKN deep neural network learns governing equations and classifies images.
problem Learning governing equations and classifying images with deep neural networks.
method Nonlocal kernel network (NKN) that is resolution independent, deep, and handles various tasks.
result NKN outperforms baseline methods in learning governing equations and image classification tasks.
A scalable deep learning framework accelerates training of large neural networks for solving 3D Poisson equations.
problem Training large-scale neural networks for solving complex PDEs efficiently.
method Combines multigrid techniques with distributed deep learning to accelerate training.
result Solves 3D Poisson equations up to 512x512x512 resolution efficiently.