# Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models

arXiv: https://arxiv.org/abs/2409.03901 · HTML: https://mlsanity.com/paper/2409.03901/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 76 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Train faster, generalize better: Stability of stochastic gradient descent](https://mlsanity.com/paper/1509.01240/) (2015)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters](https://mlsanity.com/paper/2403.11549/) (2024)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [Vision Transformer for Small-Size Datasets](https://mlsanity.com/paper/2112.13492/) (2021)
- [A Survey of Visual Transformers](https://mlsanity.com/paper/2111.06091/) (2021)
- [Scaling Laws of Synthetic Images for Model Training ... for Now](https://mlsanity.com/paper/2312.04567/) (2023)
- [PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval](https://mlsanity.com/paper/1706.03424/) (2017)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks](https://mlsanity.com/paper/2310.19909/) (2023)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [Vision-LSTM: xLSTM as Generic Vision Backbone](https://mlsanity.com/paper/2406.04303/) (2024)
- [EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction](https://mlsanity.com/paper/2205.14756/) (2022)
- [SpectralMamba: Efficient Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.08489/) (2024)
- [Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?](https://mlsanity.com/paper/1909.02436/) (2019)
- [Generic Knowledge Boosted Pre-training For Remote Sensing Images](https://mlsanity.com/paper/2401.04614/) (2024)
- [A Survey on Non-Geostationary Satellite Systems: The Communication Perspective](https://mlsanity.com/paper/2107.05312/) (2021)

## Built on by (most cited first, 8 of 8)

- [Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification](https://mlsanity.com/paper/2411.00209/) (2024)
- [A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives](https://mlsanity.com/paper/2503.09903/) (2025)
- [Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users](https://mlsanity.com/paper/2511.01990/) (2025)
- [Toward a Unified Semantic Loss Model for Deep JSCC-based Transmission of EO Imagery](https://mlsanity.com/paper/2602.00136/) (2026)
- [Iapetus: Content-Aware Hierarchical Scheduling for Collaborative ViT Inference in LEO Satellite Networks](https://mlsanity.com/paper/2609.03318/) (2026)
- [LIMODENet: Attention-Free Compact Encoders for Information-Preserving Onboard Satellite Image Restoration](https://mlsanity.com/paper/2609.14690/) (2026)
- [Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotation](https://mlsanity.com/paper/2609.37481/) (2026)
- [Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification](https://mlsanity.com/paper/2610.04073/) (2026)

## Abstract (arXiv)

Remote sensing (RS) image classification is central to Earth observation, but onboard deployment requires models that are accurate, efficient, and robust to sensor and transmission degradation. Following a train-on-ground, infer-onboard workflow, we evaluate 14 backbones, including CNNs, ResNets, compact Transformers trained from scratch, and pre-trained Vision Transformers, on EuroSAT and PatternNet. We assess clean-data performance, computational cost, power consumption, and robustness to Gaussian noise, motion blur, and an end-to-end DVB-S2(X) transmission chain with channel impairments and JPEG compression. Pre-trained Vision Transformers generally outperform models trained from scratch while providing better efficiency and corruption resilience. MobileViTV2 achieves the highest clean EuroSAT accuracy at 99.09%, whereas EfficientViT-M2 provides the strongest overall trade-off. It attains 98.76% accuracy, precision, and recall on EuroSAT and 99.52% accuracy on PatternNet, with 203.53 MFLOPs, a 38.19 MB footprint, and the best overall robustness score of 0.79. It also degrades most gracefully under transmission loss and consumes 63.35% less power than MobileViTV2 and 73.33% less than Swin Transformer. These results identify EfficientViT-M2 as a strong backbone for reliable, energy-efficient onboard RS image classification. Code for data augmentation, corruption generation, training, and inference is publicly available.