Related papers: Automatic Survey-Invariant Variable Star Classific…

How to analyse Terabytes of photometric data, and extract knowledge on variable stars? How to detect variable phenomena? How to combine different photometric bands? Which algorithm to search for periods? How to characterize and classify the…

The widespread dissemination of machine learning tools in science, particularly in astronomy, has revealed the limitation of working with simple single-task scenarios in which any task in need of a predictive model is looked in isolation,…

In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to…

We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct…

Adversarial learning has demonstrated good performance in the unsupervised domain adaptation setting, by learning domain-invariant representations. However, recent work has shown limitations of this approach when label distributions differ…

We investigate star-galaxy classification for astronomical surveys in the context of four methods enabling the interpretation of black-box machine learning systems. The first is outputting and exploring the decision boundaries as given by…

Ground-based optical surveys such as PanSTARRS, DES, and LSST, will produce large catalogs to limiting magnitudes of r > 24. Star-galaxy separation poses a major challenge to such surveys because galaxies---even very compact…

We present the results of a proof-of-concept experiment which demonstrates that deep learning can successfully be used for production-scale classification of compact star clusters detected in HST UV-optical imaging of nearby spiral galaxies…

We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…

Food authenticity studies are concerned with determining if food samples have been correctly labeled or not. Discriminant analysis methods are an integral part of the methodology for food authentication. Motivated by food authenticity…

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…

In this paper, a new approach for classification of target task using limited labeled target data as well as enormous unlabeled source data is proposed which is called self-taught learning. The target and source data can be drawn from…

We present a novel approach for classifying stars as binary or exoplanet using deep learning techniques. Our method utilizes feature extraction, wavelet transformation, and a neural network on the light curves of stars to achieve…

While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…

Ongoing or upcoming surveys such as Gaia, ZTF, or LSST will observe light-curves of billons or more astronomical sources. This presents new challenges for identifying interesting and important types of variability. Collecting a sufficient…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target…

We present a new machine learning model for estimating photometric redshifts with improved accuracy for galaxies in Pan-STARRS1 data release 1. Depending on the estimation range of redshifts, this model based on neural networks can handle…

A significant degree of misclassification of variable stars through the application of machine learning methods to survey data motivates a search for more reliable and accurate machine learning procedures, especially in light of the very…

Deep Neural Networks inherit spurious correlations embedded in training data and hence may fail to predict desired labels on unseen domains (or environments), which have different distributions from the domain used in training. Invariance…