# Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters

arXiv: https://arxiv.org/abs/2305.13456 · HTML: https://mlsanity.com/paper/2305.13456/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 65 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](https://mlsanity.com/paper/1902.06148/) (2019)
- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [What makes ImageNet good for transfer learning?](https://mlsanity.com/paper/1608.08614/) (2016)
- [Geography-Aware Self-Supervised Learning](https://mlsanity.com/paper/2011.09980/) (2020)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [ConvMAE: Masked Convolution Meets Masked Autoencoders](https://mlsanity.com/paper/2205.03892/) (2022)
- [Lightweight, Pre-trained Transformers for Remote Sensing Timeseries](https://mlsanity.com/paper/2304.14065/) (2023)
- [BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval](https://mlsanity.com/paper/2105.07921/) (2021)
- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation](https://mlsanity.com/paper/2211.07044/) (2022)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [A Billion-scale Foundation Model for Remote Sensing Images](https://mlsanity.com/paper/2304.05215/) (2023)

## Built on by (most cited first, 27 of 27)

- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [OmniSat: Self-Supervised Modality Fusion for Earth Observation](https://mlsanity.com/paper/2404.08351/) (2024)
- [Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensing](https://mlsanity.com/paper/2406.00600/) (2024)
- [Galileo: Learning Global & Local Features of Many Remote Sensing Modalities](https://mlsanity.com/paper/2502.09356/) (2025)
- [USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery](https://mlsanity.com/paper/2312.02199/) (2023)
- [PhilEO Bench: Evaluating Geo-Spatial Foundation Models](https://mlsanity.com/paper/2401.04464/) (2024)
- [Specialized Foundation Models Struggle to Beat Supervised Baselines](https://mlsanity.com/paper/2411.02796/) (2024)
- [OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation](https://mlsanity.com/paper/2511.13655/) (2025)
- [GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI](https://mlsanity.com/paper/2511.15658/) (2025)
- [Generic Knowledge Boosted Pre-training For Remote Sensing Images](https://mlsanity.com/paper/2401.04614/) (2024)
- [No One Knows the State of the Art in Geospatial Foundation Models](https://mlsanity.com/paper/2605.12678/) (2026)
- [How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?](https://mlsanity.com/paper/2409.18536/) (2024)
- [SatMamba: Development of Foundation Models for Remote Sensing Imagery Using State Space Models](https://mlsanity.com/paper/2502.00435/) (2025)
- [PRUE: A Practical Recipe for Field Boundary Segmentation at Scale](https://mlsanity.com/paper/2603.27101/) (2026)
- [GeoCrossBench: Cross-Band Generalization for Remote Sensing](https://mlsanity.com/paper/2511.02831/) (2025)
- [Cross-sensor self-supervised training and alignment for remote sensing](https://mlsanity.com/paper/2405.09922/) (2024)
- [Landsat-Bench: Datasets and Benchmarks for Landsat Foundation Models](https://mlsanity.com/paper/2506.08780/) (2025)
- [Mapping on a Budget: Optimizing Spatial Data Collection for ML](https://mlsanity.com/paper/2509.03749/) (2025)
- [Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus)](https://mlsanity.com/paper/2601.18891/) (2026)
- [Beyond Accuracy: Assessing Calibration of Geospatial Foundation Models and Their Sensitivity to Distribution Shifts](https://mlsanity.com/paper/2608.16614/) (2026)
- [Investigating Long-term Training for Remote Sensing Object Detection](https://mlsanity.com/paper/2407.15143/) (2024)
- [GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models](https://mlsanity.com/paper/2505.24340/) (2025)
- [Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery](https://mlsanity.com/paper/2601.02289/) (2026)
- [Transfer learning RGB models to hyperspectral images with trainable tensor decompositions](https://mlsanity.com/paper/2605.28331/) (2026)
- [UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures](https://mlsanity.com/paper/2606.01443/) (2026)
- [How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?](https://mlsanity.com/paper/2606.13896/) (2026)
- [MEOX: Compact Multimodal Mixture-of-Experts for Earth Observation](https://mlsanity.com/paper/2609.05351/) (2026)

## Abstract (arXiv)

Research in self-supervised learning (SSL) with natural images has progressed rapidly in recent years and is now increasingly being applied to and benchmarked with datasets containing remotely sensed imagery. A common benchmark case is to evaluate SSL pre-trained model embeddings on datasets of remotely sensed imagery with small patch sizes, e.g., 32x32 pixels, whereas standard SSL pre-training takes place with larger patch sizes, e.g., 224x224. Furthermore, pre-training methods tend to use different image normalization preprocessing steps depending on the dataset. In this paper, we show, across seven satellite and aerial imagery datasets of varying resolution, that by simply following the preprocessing steps used in pre-training (precisely, image sizing and normalization methods), one can achieve significant performance improvements when evaluating the extracted features on downstream tasks -- an important detail overlooked in previous work in this space. We show that by following these steps, ImageNet pre-training remains a competitive baseline for satellite imagery based transfer learning tasks -- for example we find that these steps give +32.28 to overall accuracy on the So2Sat random split dataset and +11.16 on the EuroSAT dataset. Finally, we report comprehensive benchmark results with a variety of simple baseline methods for each of the seven datasets, forming an initial benchmark suite for remote sensing imagery.