Related papers: AugMix: A Simple Data Processing Method to Improve…

The interest of the machine learning community in image synthesis has grown significantly in recent years, with the introduction of a wide range of deep generative models and means for training them. In this work, we propose a general…

With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning. In this paper, we introduce a new method that…

Mammographic screening is an effective method for detecting breast cancer, facilitating early diagnosis. However, the current need to manually inspect images places a heavy burden on healthcare systems, spurring a desire for automated…

Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as…

We study the problem of distribution shift generally arising in machine-learning augmented hybrid simulation, where parts of simulation algorithms are replaced by data-driven surrogates. We first establish a mathematical framework to…

Once deployed, medical image analysis methods are often faced with unexpected image corruptions and noise perturbations. These unknown covariate shifts present significant challenges to deep learning based methods trained on "clean" images.…

We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of…

Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification. Despite their huge success in image classification, the number of images…

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…

The inaccuracy of neural network models on inputs that do not stem from the training data distribution is both problematic and at times unrecognized. Model uncertainty estimation can address this issue, where uncertainty estimates are often…

A main challenge faced in the deep learning-based Underwater Image Enhancement (UIE) is that the ground truth high-quality image is unavailable. Most of the existing methods first generate approximate reference maps and then train an…

Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness,…

Recent advances in Deep Learning have greatly improved performance on various tasks such as object detection, image segmentation, sentiment analysis. The focus of most research directions up until very recently has been on beating…

Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shifts between training and test data. We propose two novel…

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowness of diffusion models by directly mapping noise to data,…

It has been shown that the majority of existing adversarial defense methods achieve robustness at the cost of sacrificing prediction accuracy. The undesirable severe drop in accuracy adversely affects the reliability of machine learning…

Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks to measure model…

Deep neural networks has been increasingly applied in fault diagnostics, where it uses historical data to capture systems behavior, bypassing the need for high-fidelity physical models. However, despite their competence in prediction tasks,…

Uncertainty estimation in machine learning is paramount for enhancing the reliability and interpretability of predictive models, especially in high-stakes real-world scenarios. Despite the availability of numerous methods, they often pose a…