mlsanityData to 14 Oct 2026

LIMODENet: Attention-Free Compact Encoders for Information-Preserving Onboard Satellite Image Restoration

arXiv 2609.14690 ↗First posted 13 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Onboard satellites must restore a channel-degraded image on a few watts, using neuromorphic accelerators (e.g., BrainChip Akida, Intel Loihi-2) that support no softmax or attention. We ask which encoder restores best under that constraint and introduce LIMODENet (LinearMix-ODENet), a 0.69M softmax-/QKV-free backbone whose residual stages read as ODE discretizations and which is empirically information-preserving (probe accuracy rises 79.9% -> 98.4% from stem to head). At iso-parameters it restores 1 dB DVB-S2X-degraded EuroSAT better than a CNN autoencoder (+1.75 dB PSNR) and a skip-connection U-Net (+1.07 dB), three seeds, non-overlapping. Unconstrained modern restorers (NAFNet, Restormer) win on fidelity; we decompose that gap: spiking-legal additive skips recover about half, and the rest traces to attention and channel gating. LIMODENet then converts end-to-end to a spiking network with zero blocked operations, versus 22-24 for the competitors: not the best restorer available, but the best verified deployable within a real power budget.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 13 Sep 2026.

Builds on

36 of 64 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2018Neural Ordinary Differential Equationscited by 3,779
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  9. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  12. 2018Group Normalizationcited by 1,524
24 more
  1. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  3. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  4. 2021Going deeper with Image Transformerscited by 764
  5. 2022Simple Baselines for Image Restorationcited by 708
  6. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
  7. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  8. 2018A Mean Field View of the Landscape of Two-Layers Neural Networkscited by 466
  9. 2018On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transportcited by 426
  10. 2018Invertible Residual Networkscited by 365
  11. 2017Stable Architectures for Deep Neural Networkscited by 341
  12. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  13. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  14. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 264
  15. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
  16. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  17. 2022Focal Modulation Networkscited by 186
  18. 2018i-RevNet: Deep Invertible Networkscited by 137
  19. 2017PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrievalcited by 97
  20. 2024Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensingcited by 47
  21. 2024Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Modelscited by 8
  22. 2024Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Visioncited by 6
  23. 2025A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectivescited by 2
  24. 2025GLUSE: Enhanced Channel-Wise Adaptive Gated Linear Units SE for Onboard Satellite Earth Observation Image Classificationcited by 1

Built on by

Not cited yet.