Related papers: Scaling Laws for Galaxy Images
The success of Large Language Models (LLMs) has established that scaling compute, through joint increases in model capacity and dataset size, is the primary driver of performance in modern machine learning. While machine learning has long…
Neural scaling laws aim to characterize how out-of-sample error behaves as a function of model and training dataset size. Such scaling laws guide allocation of a computational resources between model and data processing to minimize error.…
Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…
Data imbalance is a ubiquitous problem in machine learning. In large scale collected and annotated datasets, data imbalance is either mitigated manually by undersampling frequent classes and oversampling rare classes, or planned for with…
Semantic segmentation requires pixel-level annotation, which is time-consuming. Active Learning (AL) is a promising method for reducing data annotation costs. Due to the gap between aerial and natural images, the previous AL methods are not…
Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…
The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution. With the upcoming Large-scale Imaging Surveys, billions of galaxy images challenge astronomers to…
In this paper we present results from the weak lensing shape measurement GRavitational lEnsing Accuracy Testing 2010 (GREAT10) Galaxy Challenge. This marks an order of magnitude step change in the level of scrutiny employed in weak lensing…
Knowing the redshift of galaxies is one of the first requirements of many cosmological experiments, and as it's impossible to perform spectroscopy for every galaxy being observed, photometric redshift (photo-z) estimations are still of…
Most galaxies in the nearby Universe are gravitationally bound to a cluster or group of galaxies. Their optical contents, such as optical richness, are crucial for understanding the co-evolution of galaxies and large-scale structures in…
It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on…
The challenge of labeling large example datasets for computer vision continues to limit the availability and scope of image repositories. This research provides a new method for automated data collection, curation, labeling, and iterative…
Image Augmentations are widely used to reduce overfitting in neural networks. However, the explainability of their benefits largely remains a mystery. We study which layers of residual neural networks (ResNets) are most affected by…
The measurement of galaxy morphological parameters from astronomical images features in a wide range of modern analyses, including galaxy evolution and cosmological weak lensing studies. The precision and accuracy of morphological parameter…
For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…
Cosmological galaxy formation simulations are powerful tools to understand the complex processes that govern the formation and evolution of galaxies. However, evaluating the realism of these simulations remains a challenge. The two common…
Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the…
We present in this article an analysis of some of the properties of the density field realized in numerical simulations for power-law initial power-spectra in the case of a critical density universe. We compare our numerical results in the…
Scaling laws play an instrumental role in the sustainable improvement in model quality. Unfortunately, recommendation models to date do not exhibit such laws similar to those observed in the domain of large language models, due to the…
High-quality data is necessary for modern machine learning. However, the acquisition of such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of such annotations to determine the label of an image leads to…