mlsanityData to 7 Oct 2026

Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory

arXiv 2210.06478 ↗First posted 12 Oct 2022eess.IV astro-ph.SR cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

NASA's Solar Dynamics Observatory (SDO) mission gathers 1.4 terabytes of data each day from its geosynchronous orbit in space. SDO data includes images of the Sun captured at different wavelengths, with the primary scientific goal of understanding the dynamic processes governing the Sun. Recently, end-to-end optimized artificial neural networks (ANN) have shown great potential in performing image compression. ANN-based compression schemes have outperformed conventional hand-engineered algorithms for lossy and lossless image compression. We have designed an ad-hoc ANN-based image compression scheme to reduce the amount of data needed to be stored and retrieved on space missions studying solar dynamics. In this work, we propose an attention module to make use of both local and non-local attention mechanisms in an adversarially trained neural image compression network. We have also demonstrated the superior perceptual quality of this neural image compressor. Our proposed algorithm for compressing images downloaded from the SDO spacecraft performs better in rate-distortion trade-off than the popular currently-in-use image compression codecs such as JPEG and JPEG2000. In addition we have shown that the proposed method outperforms state-of-the art lossy transform coding compression codec, i.e., BPG.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 12 Oct 2022.

Builds on

42 of 59 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  11. 2018Variational image compression with a scale hyperpriorcited by 910
  12. 2016End-to-end Optimized Image Compressioncited by 673
30 more
  1. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  2. 2017The Perception-Distortion Tradeoffcited by 582
  3. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  4. 2017Residual Attention Network for Image Classificationcited by 385
  5. 2020High-Fidelity Generative Image Compressioncited by 331
  6. 2015A note on the evaluation of generative modelscited by 291
  7. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  8. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  9. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  10. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  11. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 168
  12. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 149
  13. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  14. 2020Nonlinear Transform Codingcited by 132
  15. 2015Density Modeling of Images using a Generalized Normalization Transformationcited by 123
  16. 2019Non-local Attention Optimized Deep Image Compressioncited by 86
  17. 2022An Introduction to Neural Data Compressioncited by 78
  18. 2020Understanding SSIMcited by 75
  19. 2016End-to-end optimization of nonlinear transform codes for perceptual qualitycited by 72
  20. 2019Computationally Efficient Neural Image Compressioncited by 31
  21. 2019A Machine Learning Dataset Prepared From the NASA Solar Dynamics Observatory Missioncited by 26
  22. 2021Morph Detection Enhanced by Structured Group Sparsitycited by 10
  23. 2019Using U-Nets to Create High-Fidelity Virtual Observations of the Solar Coronacited by 6
  24. 2021High Resolution Solar Image Generation using Generative Adversarial Networkscited by 6
  25. 2022Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translationcited by 6
  26. 2021Multi-Expert Human Action Recognition with Hierarchical Super-Class Learningcited by 5
  27. 2021DTW-Merge: A Novel Data Augmentation Technique for Time Series Classificationcited by 4
  28. 2020Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learningcited by 3
  29. 2022Information Maximization for Extreme Pose Face Recognitioncited by 3
  30. 2018Visual Object Tracking based on Adaptive Siamese and Motion Estimation Networkcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 1.

8 papers.

  1. 2023A Quality Aware Sample-to-Sample Comparison for Face Recognitioncited by 17
  2. 2023Time-Series Classification in Smart Manufacturing Systems: An Experimental Evaluation of State-of-the-Art Machine Learning Algorithmscited by 7
  3. 2023Multi-Context Dual Hyper-Prior Neural Image Compressioncited by 6
  4. 2023Multi-spectral Entropy Constrained Neural Compression of Solar Imagerycited by 1
  5. 2023Neural-based Compression Scheme for Solar Image Datacited by 1
  6. 2023Multivariate time series classification with dual attention networkcited by 0
  7. 2023Context-Aware Neural Video Compression on Solar Dynamics Observatorycited by 0
  8. 2024Neural-based Video Compression on Solar Dynamics Observatory Imagescited by 0