Related papers: Editable Neural Networks
The increasing use of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential for exhibiting ill-behaviors. While DNN verification and testing provide post hoc conclusions regarding unexpected…
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…
Generative deep learning (DL) models have been successfully adopted for vulnerability patching. However, such models require the availability of a large dataset of patches to learn from. To overcome this issue, researchers have proposed to…
The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…
In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective. When focussing on the way in which the training data are…
Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…
The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods. In this white paper, we addressed the challenge of efficiently…
Deep neural networks are susceptible to \emph{adversarial} attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks…
Deep neural networks have recently been used to edit images with great success, in particular for faces. However, they are often limited to only being able to work at a restricted range of resolutions. Many methods are so flexible that face…
Deep Neural Networks are often brittle on image classification tasks and known to misclassify inputs. While these misclassifications may be inevitable, all failure modes cannot be considered equal. Certain misclassifications (eg.…
Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic retouching systems based on supervised…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
Recent studies have shown that higher accuracy on ImageNet usually leads to better robustness against different corruptions. Therefore, in this paper, instead of following the traditional research paradigm that investigates new…
In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks.…
As humans, we can remember certain visuals in great detail, and sometimes even after viewing them once. What is even more interesting is that humans tend to remember and forget the same things, suggesting that there might be some general…
In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural…
Deep learning had been used in program analysis for the prediction of hidden software defects using software defect datasets, security vulnerabilities using generative adversarial networks as well as identifying syntax errors by learning a…
In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…
While machine learning approaches to image restoration offer great promise, current methods risk training models fixated on performing well only for image corruption of a particular level of difficulty---such as a certain level of noise or…
The rapid and widespread adoption of Deep Neural Networks (DNNs) has called for ways to test their behaviour, and many testing approaches have successfully revealed misbehaviour of DNNs. However, it is relatively unclear what one can do to…