Atomizer: Generalizing to unseen modalities by breaking images down to a set of scalars


Hugo Riffaud de Turckheim (INRIA), Diego Marcos (INRIA), Roberto Interdonato (CIRAD), Sylvain Lobry (Université de Montpellier)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

The growing number of Earth observation satellites has led to increasingly diverse remote sensing data, with varying spatial, spectral, and temporal configurations. Most existing models rely on fixed input formats and modality-specific encoders, which require retraining when new configurations are introduced, limiting their ability to generalize across modalities. We introduce Atomizer, a flexible architecture that represents remote sensing images as sets of scalars, each corresponding to a spectral band value of a pixel. Each scalar is enriched with contextual metadata (acquisition time, spatial resolution, wavelength, and bandwidth), producing an atomic representation that allows a single encoder to process arbitrary modalities without interpolation or resampling. Atomizer uses structured tokenization with Fourier features and non-uniform radial basis functions to encode content and context, and maps tokens into a latent space via cross-attention. Under modality-disjoint evaluations, Atomizer outperforms standard models and demonstrates robust performance across varying resolutions and spatial sizes.

Citation

@inproceedings{Turckheim_2025_BMVC,
author    = {Hugo Riffaud de Turckheim and Diego Marcos and Roberto Interdonato and Sylvain Lobry},
title     = {Atomizer: Generalizing to unseen modalities by breaking images down to a set of scalars},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_1058/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection