Astroformer: More Data Might not be all you need for Classification

• URL: http://arxiv.org/abs/2304.05350v2
• Date: Wed, 26 Apr 2023 20:33:41 GMT
• Title: Astroformer: More Data Might not be all you need for Classification
• Authors: Rishit Dagli
• Abstract summary: We introduce Astroformer, a method to learn from less amount of data. Our approach sets a new state-of-the-art on predicting galaxy morphologies from images on the Galaxy10 DECals dataset.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Effective Fine-Tuning of Vision-Language Models for Accurate Galaxy Morphology Analysis [3.379005517804234]
  GalaxAlign is a novel method that fine-tunes pre-trained foundation models to achieve high accuracy on astronomical tasks. Our method extends a contrastive learning architecture to align three types of data in fine-tuning.
  arXiv  Detail & Related papers  (2024-11-29T05:10:47Z)
• Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation [53.95204595640208]
  Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. Previous approaches have generated synthetic images at high resolutions without leveraging information from real images. MUSE generates images at lower resolutions while using Class Activation Maps (CAMs) to ensure that the generated images retain critical, class-specific features.
  arXiv  Detail & Related papers  (2024-11-26T02:23:31Z)
• Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior [63.64088590653005]
  We propose Diff-Mosaic, a data augmentation method based on the diffusion model. We introduce an enhancement network called Pixel-Prior, which generates highly coordinated and realistic Mosaic images. In the second stage, we propose an image enhancement strategy named Diff-Prior. This strategy utilizes diffusion priors to model images in the real-world scene.
  arXiv  Detail & Related papers  (2024-06-02T06:23:05Z)
• A Versatile Framework for Analyzing Galaxy Image Data by Implanting Human-in-the-loop on a Large Vision Model [14.609681101463334]
  We present a framework for general analysis of galaxy images based on a large vision model (LVM) plus downstream tasks (DST) Considering the low signal-to-noise ratio of galaxy images, we have incorporated a Human-in-the-loop (HITL) module into our large vision model. For object detection, trained by 1000 data points, our DST upon the LVM achieves an accuracy of 96.7%, while ResNet50 plus Mask R-CNN gives an accuracy of 93.1%.
  arXiv  Detail & Related papers  (2024-05-17T16:29:27Z)
• Discovering Galaxy Features via Dataset Distillation [7.121183597915665]
  In many applications, Neural Nets (NNs) have classification performance on par or even exceeding human capacity. Here, we apply this idea to the notoriously difficult task of galaxy classification. We present a novel way to summarize and visualize prototypical galaxy morphology through the lens of neural networks.
  arXiv  Detail & Related papers  (2023-11-29T12:39:31Z)
• A Simple and Efficient Baseline for Data Attribution on Images [107.12337511216228]
  Current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets.
  arXiv  Detail & Related papers  (2023-11-03T17:29:46Z)
• Spiral-Elliptical automated galaxy morphology classification from telescope images [0.40792653193642503]
  We develop two novel galaxy morphology statistics, descent average and descent variance, which can be efficiently extracted from telescope galaxy images. We utilize the galaxy image data from the Sloan Digital Sky Survey to demonstrate the effective performance of our proposed image statistics.
  arXiv  Detail & Related papers  (2023-10-10T22:36:52Z)
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images [53.29794593104923]
  We present a novel concept of shared-context processing for whole slide histopathology images. AMIGO uses the celluar graph within the tissue to provide a single representation for a patient. We show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data.
  arXiv  Detail & Related papers  (2023-03-01T23:37:45Z)
• Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection [57.85347204640585]
  We develop a Universal Domain Adaptation method DeepAstroUDA. It can be applied to datasets with different types of class overlap. For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets.
  arXiv  Detail & Related papers  (2022-11-01T18:07:21Z)
• InvGAN: Invertible GANs [88.58338626299837]
  InvGAN, short for Invertible GAN, successfully embeds real images to the latent space of a high quality generative model. This allows us to perform image inpainting, merging, and online data augmentation.
  arXiv  Detail & Related papers  (2021-12-08T21:39:00Z)
• Morphological classification of astronomical images with limited labelling [0.0]
  We propose an effective semi-supervised approach for galaxy morphology classification task, based on active learning of adversarial autoencoder (AAE) model. For a binary classification problem (top level question of Galaxy Zoo 2 decision tree) we achieved accuracy 93.1% on the test part with only 0.86 millions markup actions. Our best model with additional markup accuracy of 95.5%.
  arXiv  Detail & Related papers  (2021-04-27T19:26:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.