Developed AI models for multi-gas detection in near IR spectrums.
problem Detecting multiple gases in near IR spectrums.
method Used Monte Carlo KNN and multi-resolution CNN, synthesized near IR spectrums, optimized kernel sizes and channels.
result Multi-resolution CNN outperforms other models.
Develops a multi-resolution multi-task framework for integrating noisy, varying data.
problem Integrating evidence from multiple observation processes with varying resolutions and noise levels.
method Multi-resolution Multi-task Gaussian Processes (MRGP) framework, shallow and deep Gaussian Process mixtures.
result Generalizes and outperforms state-of-the-art GP compositions, offering efficient corrections and approximations.
Dugong models multi-resolution weak supervision for sequential data.
problem Estimating unknown accuracies and correlations of weak supervision sources for sequential data.
method Dugong, a framework that models multi-resolution weak supervision sources with complex correlations, using parameter sharing to improve sample complexity.
result Dugong outperforms traditional supervision by 36.8 F1 points on clinician-validated labels for biomedical video repositories.
Proposes a model to handle mobile health data with irregular measurements.
problem Handling heterogeneous, multi-resolution data in mobile health.
method Individualized dynamic latent factor model for irregular multi-resolution time series data.
result Superior performance compared to existing methods in simulation and smartwatch data applications.
Modeling complex systems with multi-resolution data and causal dependencies.
problem Accurate prediction of complex systems with varying causal dependencies and multi-resolution data.
method Score-based Variational Graphical Diffusion Model (Temporal-SVGDM) that constructs individual SDEs for each variable at its native resolution and couples them through a causal score mechanism.
result Improved prediction accuracy and causal understanding compared to existing methods, especially in temporal scenarios.
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.
MRIF models dynamic user interests at multiple temporal-ranges.
problem Capturing dynamic and multi-resolution user interests in recommendation.
method Multi-resolution Interest Fusion (MRIF) model that considers both temporal-ranges and drifts in user interests.
result MRIF outperforms state-of-the-art recommendation methods consistently.
This paper analyzes the use of 3D Convolutional Neural Networks for brain tumor segmentation in MR images. We address the problem using three different architectures that combine fine and coarse features to obtain the final segmentation. We compare three different networks that use multi-resolution features in terms of…
The paper reformulates U-Nets as wavelet-based models and applies this to hierarchical VAEs.
problem Theoretical understanding and regularization properties of U-Nets and their relationship to wavelets.
method Formulating a multi-resolution framework to identify U-Nets as finite-dimensional truncations of infinite-dimensional models, proving average pooling corresponds to projection, and identifying HVAEs as discretizations of multi-resolution diffusion processes.
result HVAEs learn a time representation allowing for improved parameter efficiency through weight-sharing.
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.
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.
Proposes a multi-resolution model for prostate cancer classification using mpMRI.
problem Improving voxel-wise classification of prostate cancer using multi-parametric MRI data.
method Multi-resolution Super Learner framework combining local base learners at multiple resolutions and spatial Gaussian kernel smoothing.
result Enhanced voxel-wise classification of prostate cancer status and clinical significance.
A novel multi-resolution Gaussian process model for efficient time traversal.
problem Inference for long sequences with fast and slow transitions is difficult.
method A novel Gaussian process state-space architecture composed of multiple components, each trained on a different resolution.
result The combined model allows efficient inference for arbitrarily long sequences with complex dynamics.
MDEQ models learn multi-resolution features efficiently.
problem Large-scale, hierarchical pattern recognition.
method Implicit differentiation, multiscale deep equilibrium model.
result MDEQs achieve performance on par with recent models.
A new method generates graphs with hierarchical structures.
problem Generating graphs with natural hierarchical structures.
method Recursively generates community structures at multiple resolutions, parallel generation of all sub-structures.
result Improves generative performance on multiple graph datasets.
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.
MPPN network improves long-term time series forecasting accuracy.
problem Inaccurate long-term time series forecasting due to noise and lack of interpretability.
method MPPN network constructs context-aware multi-resolution semantic units and employs multi-periodic pattern mining and channel adaptive module.
result MPPN significantly outperforms state-of-the-art methods on nine real-world benchmarks.
A new neural network separates singing voices more effectively.
problem Separating singing voices from mixed signals with high accuracy.
method MBR-FCN that processes different frequency bands with varying resolutions and filters.
result The MBR-FCN achieves better performance with fewer parameters.
Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …
Missing values, irregularly collected samples, and multi-resolution signals commonly occur in multivariate time series data, making predictive tasks difficult. These challenges are especially prevalent in the healthcare domain, where patients' vital signs and electronic records are collected at different frequencies an…
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.
A new algorithm reduces distributed learning error to near-optimal levels.
problem Optimal one-shot distributed learning with limited samples per machine.
method Multi-Resolution Estimator (MRE) algorithm for parameter estimation.
result The MRE algorithm achieves error bounds approaching existing lower bounds.
Proposes a method to select features for deep learning in noisy, high-dimensional data.
problem Feature selection for deep learning in ultra-high dimensional and highly correlated data.
method Data-adaptive multi-resolutional screening and cleaning with deep learning.
result Achieves high power while keeping false discovery rate low.
Predicting interactions between structured entities lies at the core of numerous tasks such as drug regimen and new material design. In recent years, graph neural networks have become attractive. They represent structured entities as graphs and then extract features from each individual graph using graph convolution op…
Improved speech enhancement with MNTFA using time-frequency attention.
problem Speech enhancement with limited model size and memory.
method Designing MNTFA with self-attention modules for long sequences and joint training.
result MNTFA achieves better performance with fewer parameters than DPCRN.
SPECTRA improves probabilistic energy forecasting by separating trends and uncertainties.
problem Interacting uncertainties from renewable intermittency, demand flexibility, market volatility, and weather impact probabilistic forecasts.
method Adaptive state-space exogenous context and temporal-frequency resolution architecture.
result Achieved best CRPS in 14 out of 18 settings, reducing CRPS by 5.74% and upper-tail quantile risk by 7.27%.
Motivated by the practical demands for simplification of data towards being consistent with human thinking and problem solving as well as tolerance of uncertainty, information granules are becoming important entities in data processing at different levels of data abstraction. This paper proposes a method to construct c…
A new numerical framework simplifies elastic surface matching and comparison.
problem Challenging problem in surface comparison and matching in computer vision.
method Relaxing the geodesic boundary constraint using a varifold fidelity metric.
result Flexibility to deal with arbitrary topologies and sampling patterns, scalability to large meshes.
StreaMRAK improves KRR for streaming data.
problem Streaming data with memory constraints.
method Divides problem into levels of resolution, sub-sampling.
result Efficiently integrates new samples, reduces memory and complexity.
New model tackles complex spatio-temporal causal inference with dynamic confounders and functional data.
problem Complex spatio-temporal dynamics and unmeasured confounders hinder causal inference.
method PFD-BDCM, a unified generative framework for spatio-temporal dependencies, functional data, and dynamic confounding.
result PFD-BDCM outperforms existing methods across observational, interventional, and counterfactual queries.
Trends in terrestrial temperature variability are perhaps more relevant for species viability than trends in mean temperature. In this paper, we develop methodology for estimating such trends using multi-resolution climate data from polar orbiting weather satellites. We derive two novel algorithms for computation that …
A new method for hierarchical clustering is presented. It combines treelets, a particular multiscale decomposition of data, with a projection on a reproducing kernel Hilbert space. The proposed approach, called kernel treelets (KT), effectively substitutes the correlation coefficient matrix used in treelets with a symm…
New approximative kernels improve PDE-G-CNNs for geometric deep learning.
problem Inaccurate approximations of exact kernels in PDE-G-CNNs.
method Developed new approximative kernels that work regardless of spatial anisotropy.
result New kernels provide better error estimates and maintain reflectional symmetries.
In recent years, deep learning poses a deep technical revolution in almost every field and attracts great attentions from industry and academia. Especially, the convolutional neural network (CNN), one representative model of deep learning, achieves great successes in computer vision and natural language processing. How…
We attempt to interpret how adversarially trained convolutional neural networks (AT-CNNs) recognize objects. We design systematic approaches to interpret AT-CNNs in both qualitative and quantitative ways and compare them with normally trained models. Surprisingly, we find that adversarial training alleviates the textur…
Convolutional Neural Networks (CNNs) have revolutionized performances in several machine learning tasks such as image classification, object tracking, and keyword spotting. However, given that they contain a large number of parameters, their direct applicability into low resource tasks is not straightforward. In this w…
Simplified Butterfly-Net2 improves CNN efficiency in solving PDEs and signal processing tasks.
problem Improving CNN efficiency in solving PDEs and signal processing tasks.
method Introducing BNet2, a simplified Butterfly-Net, and Fourier transform initialization.
result BNet2 achieves similar accuracy as CNN but with fewer parameters and improves accuracy over randomly initialized CNN.
2D CNNs approximate Korobov functions with near-optimal rates.
problem Approximating Korobov functions using 2D CNNs.
method Constructive approach for 2D CNNs with ReLU activations and fully connected layers.
result 2D CNNs achieve near-optimal approximation rates for Korobov functions.
New metrics differentiate effective OOD sets for training calibrated CNNs.
problem Vanilla CNNs struggle with out-of-distribution (OOD) samples.
method Developed metrics based on generalization errors of Augmented-CNN.
result Most protective OOD sets lead to better A-CNN performance.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.
problem Checkerboard artifacts in CNNs during upsampling and strided convolution.
method Fixed convolutional layer with adjustable smoothness, applied to four CNNs and GANs.
result Significantly improves classification performance and image generation quality.
In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time…
The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive task. We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolu…
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
problem Limited memory on embedded FPGAs restricts CNN performance.
method Software and hardware design tool for FPGA resource-aware CNN accelerator.
result 3% accuracy loss with 15.75x speedup on image classification.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
problem Improving CNNs for robust acoustic scene classification.
method Investigated different receptive field configurations for various CNN architectures and introduced Frequency Aware CNNs.
result Several well-performing submissions to DCASE 2019 Challenge were achieved.
Simple 1D-CNN network predicts electricity loads 36 hours ahead.
problem Forecasting electricity loads for future time periods.
method Used a one-dimensional CNN with parameter scanning to optimize kernel size, filters, and dense size.
result Good forecast quality achieved with basic CNN architectures.
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of two- dimensional time-frequency fea…
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explaine…