Search Results for author:
Found 31 papers, 12 papers with code
Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport
In this regard, previous WGF models employ the JKO scheme and parametrize transport map for each JKO step.
Spatial-and-Frequency-aware Restoration method for Images based on Diffusion Models
We comprehensively evaluate the performance of our model on a variety of noisy inverse problems, including inpainting, denoising, and super-resolution.
Approximating Numerical Fluxes Using Fourier Neural Operators for Hyperbolic Conservation Laws
To this end, we developed loss functions inspired by established numerical schemes related to conservation laws and approximated numerical fluxes using Fourier neural operators (FNOs).
$p$-Poisson surface reconstruction in curl-free flow from point clouds
For efficient training, we develop a variable splitting structure by introducing a gradient of the SDF as an auxiliary variable and impose the $p$-Poisson equation directly on the auxiliary variable as a hard constraint.
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more relatively rare conditions.
Analyzing and Improving Optimal-Transport-based Adversarial Networks
In this paper, we begin by unifying these OT-based adversarial methods within a single framework.
AdaptiveRec: Adaptively Construct Pairs for Contrastive Learning in Sequential Recommendation
This paper presents a solution to the challenges faced by contrastive learning in sequential recommendation systems.
Feature-aligned N-BEATS with Sinkhorn divergence
We propose Feature-aligned N-BEATS as a domain-generalized time series forecasting model.
Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport
In this paper, we propose a novel generative model based on the semi-dual formulation of Unbalanced Optimal Transport (UOT).
AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Scheme
Mechanical defects in real situations affect observation values and cause abnormalities in multivariate time series, such as sensor values or network data.
Restoration based Generative Models
Also, we propose a multi-scale training, which improves the performance compared to the diffusion process, by taking advantage of the flexibility of the forward process.
Learning PDE Solution Operator for Continuous Modeling of Time-Series
Learning underlying dynamics from data is important and challenging in many real-world scenarios.
A Unified Framework for Robustness on Diverse Sampling Errors
Instead of assuming and fixing the target distribution at training, our proposed approach allows adjusting the feature space the model refers to at every prediction, i. e., instance-wise adaptive inference.
Minimal Width for Universal Property of Deep RNN
In this study, we prove the universality of deep narrow RNNs and show that the upper bound of the minimum width for universality can be independent of the length of the data.
Universal Approximation Property of Fully Convolutional Neural Networks with Zero Padding
Despite its widespread adoption, our understanding of its universal approximation properties has been limited due to its intricate nature.
Finding the global semantic representation in GAN through Frechet Mean
This semantic basis represents sample-independent meaningful perturbations that change the same semantic attribute of an image on the entire latent space.
Bounding the Rademacher Complexity of Fourier neural operators
Using capacity based on these norms, we bound the generalization error of the model.
Self-Knowledge Distillation via Dropout
In this paper, we propose a simple and effective self-knowledge distillation method using a dropout (SD-Dropout).
Analyzing the Latent Space of GAN through Local Dimension Estimation
In this paper, we approach this problem through a geometric analysis of latent spaces as a manifold.
A Conservative Approach for Unbiased Learning on Unknown Biases
Although convolutional neural networks (CNNs) achieve state-of-the-art in image classification, recent works address their unreliable predictions due to their excessive dependence on biased training data.
Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
Deep probabilistic generative models facilitate OOD detection by estimating the likelihood of a data sample.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
The global warpage implies that the latent space is not well-aligned globally and therefore the global traversal directions are bound to show limited success on it.
High-Frequency aware Perceptual Image Enhancement
In this paper, we introduce a novel deep neural network suitable for multi-scale analysis and propose efficient model-agnostic methods that help the network extract information from high-frequency domains to reconstruct clearer images.
OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space
Specifically, we employ orthogonal low-rank embedding in the latent space to disentangle the features in the latent space using mutual class information.
MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks
Experimental results on both synthetic and real-world rainy datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art models.
Ranked #1 on
Single Image Deraining
on RainCityscapes
Discond-VAE: Disentangling Continuous Factors from the Discrete
To represent these generative factors of data, we introduce two sets of continuous latent variables, private variable and public variable.
Blur Invariant Kernel-Adaptive Network for Single Image Blind deblurring
Subsequently, we propose a deblurring network that restores sharp images using the estimated blur kernel.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Membership Inference Attacks Against Object Detection Models
Machine learning models can leak information regarding the dataset they have trained.
Attention routing between capsules
We replace the dynamic routing and squash activation function of the capsule network with dynamic routing (CapsuleNet) with the attention routing and capsule activation.
Financial series prediction using Attention LSTM
In recent times, deep learning methods (especially time series analysis) have performed outstandingly for various industrial problems, with better prediction than machine learning methods.
