Related papers: Unsupervised Classification of Variable Stars

Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high. To overcome this problem, we propose a new weakly-supervised learning…

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…

The rise of synoptic sky surveys has ushered in an era of big data in time-domain astronomy, making data science and machine learning essential tools for studying celestial objects. While tree-based models (e.g. Random Forests) and deep…

We present a fast algorithm to produce light curves of distant stars undergoing microlensing near critical curves. The need of these type of algorithms is motivated by recent observations of microlensing events of distant stars at high…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

There exist a variety of star-galaxy classification techniques, each with their own strengths and weaknesses. In this paper, we present a novel meta-classification framework that combines and fully exploits different techniques to produce a…

We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning solution for the under-explored problem…

Unsupervised feature selection aims to identify a compact subset of features that captures the intrinsic structure of data without supervised label. Most existing studies evaluate the performance of methods using the single-label dataset…

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning. Existing unsupervised and self-supervised…

This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried by a mobile robot. A…

Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

The lack of large labeled medical imaging datasets, along with significant inter-individual variability compared to clinically established disease classes, poses significant challenges in exploiting medical imaging information in a…

Recent advances in contrastive learning have enlightened diverse applications across various semi-supervised fields. Jointly training supervised learning and unsupervised learning with a shared feature encoder becomes a common scheme.…

In the context of the highly increasing number of features that are available nowadays we design a robust and fast method for feature selection. The method tries to select the most representative features that are independent from each…

In the era of rapidly increasing amounts of time series data, classification of variable objects has become the main objective of time-domain astronomy. Classification of irregularly sampled time series is particularly difficult because the…

Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large scale datasets. In this…

In unsupervised learning, the training data for deep learning does not come with any labels, thus forcing the algorithm to discover hidden patterns in the data for discerning useful information. This, in principle, could be a powerful tool…

In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics,…