Related papers: Machine Learning for Transient Recognition in Diff…

Training data plays an essential role in modern applications of machine learning. However, gathering labeled training data is time-consuming. Therefore, labeling is often outsourced to less experienced users, or completely automated. This…

The scientific study of the Solar System's minor bodies ultimately starts with a search for those bodies. This chapter presents a review of the use of machine learning techniques to find moving objects, both natural and artificial, in…

Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated…

Recently, machine learning-based real/bogus (RB) classifiers have demonstrated effectiveness in filtering out artifacts and identifying genuine transients in real-time astronomical surveys. However, the rarity of transient events and the…

We present a comparison of several Difference Image Analysis (DIA) techniques, in combination with Machine Learning (ML) algorithms, applied to the identification of optical transients associated with gravitational wave events. Each…

Distinguishing manipulated from real images is becoming increasingly difficult as new sophisticated image forgery approaches come out by the day. Naive classification approaches based on Convolutional Neural Networks (CNNs) show excellent…

Current contrastive learning methods use random transformations sampled from a large list of transformations, with fixed hyperparameters, to learn invariance from an unannotated database. Following previous works that introduce a small…

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the…

Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for…

In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vision. In a first…

The need for large annotated image datasets for training Convolutional Neural Networks (CNNs) has been a significant impediment for their adoption in computer vision applications. We show that with transfer learning an effective object…

There are many occasions when one does not have complete information in order to classify objects into different classes, and yet it is important to do the best one can since other decisions depend on that. In astronomy, especially…

The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of…

Model-based optimization (MBO) is increasingly applied to design problems in science and engineering. A common scenario involves using a fixed training set to train models, with the goal of designing new samples that outperform those…

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

Employing machine learning models in the real world requires collecting large amounts of data, which is both time consuming and costly to collect. A common approach to circumvent this is to leverage existing, similar data-sets with large…

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in…

We investigate the use of Convolutional Neural Networks (including the modern ConvNeXt network family) to classify transient noise signals (i.e.~glitches) and gravitational waves in data from the Advanced LIGO detectors. First, we use…

New deep-learning architectures are created every year, achieving state-of-the-art results in image recognition and leading to the belief that, in a few years, complex tasks such as sign language translation will be considerably easier,…

Prevailing fingerprint recognition systems are vulnerable to spoof attacks. To mitigate these attacks, automated spoof detectors are trained to distinguish a set of live or bona fide fingerprints from a set of known spoof fingerprints.…