# Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder

arXiv: https://arxiv.org/abs/2604.16952 · HTML: https://mlsanity.com/paper/2604.16952/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 63 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2110.08733/) (2021)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders](https://mlsanity.com/paper/2311.00566/) (2023)
- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)
- [Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model](https://mlsanity.com/paper/2208.03987/) (2022)
- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Towards Geospatial Foundation Models via Continual Pretraining](https://mlsanity.com/paper/2302.04476/) (2023)
- [Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation](https://mlsanity.com/paper/2403.15356/) (2024)
- [SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion](https://mlsanity.com/paper/1906.07789/) (2019)
- [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)
- [Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing](https://mlsanity.com/paper/2310.18653/) (2023)
- [SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection](https://mlsanity.com/paper/2403.06534/) (2024)
- [FLAIR: VLM with Fine-grained Language-informed Image Representations](https://mlsanity.com/paper/2412.03561/) (2024)
- [SpaceNet 6: Multi-Sensor All Weather Mapping Dataset](https://mlsanity.com/paper/2004.06500/) (2020)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [Bridging Remote Sensors with Multisensor Geospatial Foundation Models](https://mlsanity.com/paper/2404.01260/) (2024)

## Built on by (most cited first, 1 of 1)

- [SAREO-FM: Decoupled Semantic Supervision for SAR-EO Foundation Models](https://mlsanity.com/paper/2610.09317/) (2026)

## Abstract (arXiv)

Learning robust representations across extremely heterogeneous modalities remains a fundamental challenge in multi-modal vision. As a critical and profound instantiation of this challenge, high-resolution (HR) joint optical and synthetic aperture radar (SAR) pretraining seeks modality synergy to mutually enhance single-source representations; its potential is severely hindered by the Heterogeneity-Resolution Paradox: finer spatial scales drastically amplify the physical divergence between complex radar geometries and non-homologous optical textures. Consequently, migrating medium-resolution-oriented rigid alignment paradigms to HR scenarios triggers either severe feature suppression to force equivalence, or feature contamination driven by extreme epistemic uncertainty. Both extremes inevitably culminate in profound representation degradation and negative transfer. To overcome this bottleneck, we propose CoDe-MAE, pioneering a textitbetter synergy with less alignment philosophy. First, Optical-anchored Knowledge Distillation (OKD) implicitly regularizes SAR's speckle noise by mapping it into a pure semantic manifold. Building on this, Conditioned Contrastive Learning (CCL) utilizes a gradient buffering mechanism to align shared consensus while safely preserving divergent physical signatures. Concurrently, Cross-Modal Degraded Reconstruction (CDR) deliberately strips non-homologous spectral pseudo-features, truncating the inherently ill-posed mapping to capture true structural invariants. Extensive analyses validate our theoretical claims. Pretrained on 1M samples, CoDe-MAE demonstrates remarkable data efficiency, successfully preventing representation degradation and establishing new state-of-the-art performance across diverse single- and bi-modal downstream tasks, substantially outperforming foundation models scaled on vastly larger datasets.