Search Results for author:
Found 34 papers, 19 papers with code
Indirectly Parameterized Concrete Autoencoders
Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly.
Stable Autonomous Flow Matching
Despite this, connections between control theory and generative models in the literature are sparse, even though there are several machine learning applications with physically stable data points.
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events.
Logistic-Normal Likelihoods for Heteroscedastic Label Noise
A natural way of estimating heteroscedastic label noise in regression is to model the observed (potentially noisy) target as a sample from a normal distribution, whose parameters can be learned by minimizing the negative log-likelihood.
Predicting the wall-shear stress and wall pressure through convolutional neural networks
At $Re_{\tau}=550$, both FCN and R-Net can take advantage of the self-similarity in the logarithmic region of the flow and predict the velocity-fluctuation fields at $y^{+} = 50$ using the velocity-fluctuation fields at $y^{+} = 100$ as input with about 10% error in prediction of streamwise-fluctuations intensity.
On the Lipschitz Constant of Deep Networks and Double Descent
Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms controlling such factors in practice.
Unsupervised Flood Detection on SAR Time Series
Our proposed CD model is evaluated on flood detection data.
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation.
Deep Double Descent via Smooth Interpolation
The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double descent curve for the test error.
PatchDropout: Economizing Vision Transformers Using Patch Dropout
This simple approach, PatchDropout, reduces FLOPs and memory by at least 50% in standard natural image datasets such as ImageNet, and those savings only increase with image size.
Towards Self-Supervised Learning of Global and Object-Centric Representations
Self-supervision allows learning meaningful representations of natural images, which usually contain one central object.
Are All Linear Regions Created Equal?
The number of linear regions has been studied as a proxy of complexity for ReLU networks.
An analysis of over-sampling labeled data in semi-supervised learning with FixMatch
Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches.
CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
Interval and large invasive breast cancers, which are associated with worse prognosis than other cancers, are usually detected at a late stage due to false negative assessments of screening mammograms.
Consistency Regularization Can Improve Robustness to Label Noise
Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning.
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
Prior works have found it beneficial to combine provably noise-robust loss functions e. g., mean absolute error (MAE) with standard categorical loss function e. g. cross entropy (CE) to improve their learnability.
Ranked #17 on
Image Classification
on mini WebVision 1.0
FEW-SHOTLEARNING WITH WEAK SUPERVISION
Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.
From coarse wall measurements to turbulent velocity fields through deep learning
The method is applied both for the resolution enhancement of wall fields and the estimation of wall-parallel velocity fields from coarse wall measurements of shear stress and pressure.
Fluid Dynamics
Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
With this in mind, we trained networks using three different criteria to select the positive training data (i. e. images from patients that will develop cancer): an inherent risk model trained on images with no visible signs of cancer, a cancer signs model trained on images containing cancer or early signs of cancer, and a conflated model trained on all images from patients with a cancer diagnosis.
Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
Visual relationship detection is fundamental for holistic image understanding.
Recurrent neural networks and Koopman-based frameworks for temporal predictions in a low-order model of turbulence
We also observe that using a loss function based only on the instantaneous predictions of the chaotic system can lead to suboptimal reproductions in terms of long-term statistics.
Hyperplane Arrangements of Trained ConvNets Are Biased
We investigate the geometric properties of the functions learned by trained ConvNets in the preactivation space of their convolutional layers, by performing an empirical study of hyperplane arrangements induced by a convolutional layer.
On the use of recurrent neural networks for predictions of turbulent flows
We also observe that using a loss function based only on the instantaneous predictions of the flow may not lead to the best predictions in terms of turbulence statistics, and it is necessary to define a stopping criterion based on the computed statistics.
GraphQA: Protein Model Quality Assessment using Graph Convolutional Network
Proteins are ubiquitous molecules whose function in biological processes is determined by their 3D structure.
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks.
Explainability Techniques for Graph Convolutional Networks
Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them.
The role of artificial intelligence in achieving the Sustainable Development Goals
We find that AI can support the achievement of 128 targets across all SDGs, but it may also inhibit 58 targets.
GANtruth - an unpaired image-to-image translation method for driving scenarios
In this work, we propose a novel method for constraining the output space of unpaired image-to-image translation.
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
We show that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models.
Spotlight the Negatives: A Generalized Discriminative Latent Model
Discriminative latent variable models (LVM) are frequently applied to various visual recognition tasks.
Persistent Evidence of Local Image Properties in Generic ConvNets
Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary information associated with the capture of the image or the variation within the object class.
Factors of Transferability for a Generic ConvNet Representation
In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target).
Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach
Finally, we show that state of the art object detection methods (e. g. DPM) are unable to use the tails of this distribution comprising 50\% of the training samples.
CNN Features off-the-shelf: an Astounding Baseline for Recognition
We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13.
