Related papers: Representation learning for automated spectroscopi…
Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…
Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning…
We present a probabilistic autoencoder (PAE) framework for galaxy spectral energy distribution (SED) modeling and redshift estimation, applied to synthetic SPHEREx 102-band spectrophotometry. Our PAE learns a compact latent representation…
Representation learning aims to extract meaningful lower-dimensional embeddings from data, known as representations. Despite its widespread application, there is no established definition of a ``good'' representation. Typically, the…
This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…
In addition to the maximum likelihood approach, there are two other methods which are commonly used to reconstruct the true redshift distribution from photometric redshift datasets: one uses a deconvolution method, and the other a…
Unsupervised learning, a branch of machine learning that can operate on unlabelled data, has proven to be a powerful tool for data exploration and discovery in astronomy. As large surveys and new telescopes drive a rapid increase in data…
We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and…
Optical spectra contain a wealth of information about the physical properties and formation histories of galaxies. Often though, spectra are too noisy for this information to be accurately retrieved. In this study, we explore how machine…
A new approach to estimating photometric redshifts - using Artificial Neural Networks (ANNs) - is investigated. Unlike the standard template-fitting photometric redshift technique, a large spectroscopically-identified training set is…
Learning to fuse vision and language information and representing them is an important research problem with many applications. Recent progresses have leveraged the ideas of pre-training (from language modeling) and attention layers in…
From SDSS commissioning photometric and spectroscopic data, we investigate the utility of photometric redshift techniques to the task of estimating QSO redshifts. We consider empirical methods (e.g. nearest-neighbor searches and polynomial…
Future radio surveys will generate catalogues of tens of millions of radio sources, for which redshift estimates will be essential to achieve many of the science goals. However, spectroscopic data will be available for only a small fraction…
Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely…
We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image elements to feature…
In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation. Our philosophy is to deconstruct a DDM, gradually transforming it into a classical…
Handling big data has largely been a major bottleneck in traditional statistical models. Consequently, when accurate point prediction is the primary target, machine learning models are often preferred over their statistical counterparts for…
Large-scale volumetric medical images with annotation are rare, costly, and time prohibitive to acquire. Self-supervised learning (SSL) offers a promising pre-training and feature extraction solution for many downstream tasks, as it only…
In cosmological analyses, precise redshift determination remains pivotal for understanding cosmic evolution. However, with only a fraction of galaxies having spectroscopic redshifts (spec-$z$s), the challenge lies in estimating redshifts…
Self-supervised depth estimation has shown its great effectiveness in producing high quality depth maps given only image sequences as input. However, its performance usually drops when estimating on border areas or objects with thin…