Related papers: Comparison of Multi-Class and Binary Classificatio…

We propose a novel technique to refine the modelling of galaxy clusters mass distribution using gravitational lensing. The idea is to combine the strengths of both "parametric" and "non-parametric" methods to improve the quality of the fit.…

The combination of deep exposures and high resolution offered by telescopes in space allows the detection of lensing over a wide range of source redshifts and lens masses. As an example, we model a lens candidate found in the southern…

Various galaxy merger detection methods have been applied to diverse datasets. However, it is difficult to understand how they compare. We aim to benchmark the relative performance of machine learning (ML) merger detection methods. We…

The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…

Classification of galactic morphologies is a crucial task in galactic astronomy, and identifying fine structures of galaxies (e.g., spiral arms, bars, and clumps) is an essential ingredient in such a classification task. However, seeing…

Although point caustics harbour a larger potential for measuring the brightness profile of stars during the course of a microlensing event than (line-shaped) fold caustics, the effect of lens binarity significantly limits the achievable…

We investigate the problem of multiclass classification with rejection, where a classifier can choose not to make a prediction to avoid critical misclassification. First, we consider an approach based on simultaneous training of a…

Estimating the ratio of two probability densities from a finite number of observations is a central machine learning problem. A common approach is to construct estimators using binary classifiers that distinguish observations from the two…

Gravitational wave searches rely on a combination of methods, including matched filtering, coherent analyses, and more recent machine learning based pipelines. For compact binary coalescences, where signals originate from the relativistic…

We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag…

Few-shot learning for fine-grained image classification has gained recent attention in computer vision. Among the approaches for few-shot learning, due to the simplicity and effectiveness, metric-based methods are favorably state-of-the-art…

Learning classifiers using skewed or imbalanced datasets can occasionally lead to classification issues; this is a serious issue. In some cases, one class contains the majority of examples while the other, which is frequently the more…

Machine learning can greatly benefit from providing learning algorithms with pairs of contrastive training examples -- typically pairs of instances that differ only slightly, yet have different class labels. Intuitively, the difference in…

Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

For the first detection of a novel astrophysical phenomenon, scientific standards are particularly high. Especially in a multi-messenger context, there are also opportunity costs to follow-up observations on any detection claims. So in…

Contrastive learning predicts whether two images belong to the same category by training a model to make their feature representations as close or as far away as possible. In this paper, we rethink how to mine samples in contrastive…

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling complex scenarios with…

In supervised learning, we often face with ambiguous (A) samples that are difficult to label even by domain experts. In this paper, we consider a binary classification problem in the presence of such A samples. This problem is substantially…

The number of strong lens systems is expected to increase significantly in ongoing and upcoming surveys. With an increase in the total number of such systems we expect to discover many configurations that correspond to unstable caustics. In…