Related papers: Data--driven Image Restoration with Option--driven…

Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data augmentation has been gradually replaced by automatically learned augmentation policy. Through finding…

In recent years, deep learning has achieved remarkable empirical success for image reconstruction. This has catalyzed an ongoing quest for precise characterization of correctness and reliability of data-driven methods in critical use-cases,…

In this work, we investigate the application of deep learning methods for computed tomography in the context of having a low-data regime. As motivation, we review some of the existing approaches and obtain quantitative results after…

Deep learning methods are becoming widely used for restoration of defects associated with fluorescence microscopy imaging. One of the major challenges in application of such methods is the availability of training data. In this work, we…

This paper investigates the impact of various data augmentation techniques on the performance of object detection models. Specifically, we explore classical augmentation methods, image compositing, and advanced generative models such as…

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color…

An alternative data-driven modeling approach has been proposed and employed to gain fundamental insights into robot motion interaction with granular terrain at certain length scales. The approach is based on an integration of dimension…

Light scattering and aberrations limit optical microscopy in biological tissue, which motivates the development of adaptive optics techniques. Here, we develop a method for adaptive optics with reflected light and deep neural networks…

The popularity of data augmentation techniques in machine learning has increased in recent years, as they enable the creation of new samples from existing datasets. Rotational augmentation, in particular, has shown great promise by…

The recent explosion in applications of machine learning to satellite imagery often rely on visible images and therefore suffer from a lack of data during the night. The gap can be filled by employing available infra-red observations to…

Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as…

Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks, in which noise is added to…

Optical Earth observation satellites acquire images worldwide , covering up to several million square kilometers every day. The complexity of scheduling acquisitions for such systems increases exponentially when considering the…

Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as…

This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on…

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…

An array of large observational programs using ground-based and space-borne telescopes is planned in the next decade. The forthcoming wide-field sky surveys are expected to deliver a sheer volume of data exceeding an exabyte. Processing the…

Object detection and classification for aircraft are the most important tasks in the satellite image analysis. The success of modern detection and classification methods has been based on machine learning and deep learning. One of the key…

An unbiased method for improving the resolution of astronomical images is presented. The strategy at the core of this method is to establish a linear transformation between the recorded image and an improved image at some desirable…

Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and…