REVIEW 2 cited by
Astroformer: More Data Might not be all you need for Classification
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Recent advancements in areas such as natural language processing and computer vision rely on intricate and massive models that have been trained using vast amounts of unlabelled or partly labeled data and training or deploying these state-of-the-art methods to resource constraint environments has been a challenge. Galaxy morphologies are crucial to understanding the processes by which galaxies form and evolve. Efficient methods to classify galaxy morphologies are required to extract physical information from modern-day astronomy surveys. In this paper, we introduce Astroformer, a method to learn from less amount of data. We propose using a hybrid transformer-convolutional architecture drawing much inspiration from the success of CoAtNet and MaxViT. Concretely, we use the transformer-convolutional hybrid with a new stack design for the network, a different way of creating a relative self-attention layer, and pair it with a careful selection of data augmentation and regularization techniques. Our approach sets a new state-of-the-art on predicting galaxy morphologies from images on the Galaxy10 DECals dataset, a science objective, which consists of 17736 labeled images achieving 94.86% top-$1$ accuracy, beating the current state-of-the-art for this task by 4.62%. Furthermore, this approach also sets a new state-of-the-art on CIFAR-100 and Tiny ImageNet. We also find that models and training methods used for larger datasets would often not work very well in the low-data regime.
Forward citations
Cited by 2 Pith papers
-
Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso
CM-GLasso jointly estimates shared and class-specific precision matrices from aligned vision-language features via cross-attention priors and ADMM, claiming SOTA on eight classification and segmentation benchmarks.
-
Detecting Galactic Rings in the DESI Legacy Imaging Surveys with Semi-Supervised Deep Learning
A semi-supervised GAN trained on expert-verified ringed galaxies identifies 62,962 ringed galaxy candidates among 748,601 bright, low-redshift galaxies in the DESI Legacy Imaging Surveys, the largest ringed-galaxy cat...
Discussion (0). Continue with ORCID to comment.