L-MCAT: Unpaired Multimodal Transformer with Contrastive Attention for Label-Efficient Satellite Image Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Goswami, Mitul, Goswami, Mrinal
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911079308722176
author Goswami, Mitul
Goswami, Mrinal
author_facet Goswami, Mitul
Goswami, Mrinal
contents We propose the Lightweight Multimodal Contrastive Attention Transformer (L-MCAT), a novel transformer-based framework for label-efficient remote sensing image classification using unpaired multimodal satellite data. L-MCAT introduces two core innovations: (1) Modality-Spectral Adapters (MSA) that compress high-dimensional sensor inputs into a unified embedding space, and (2) Unpaired Multimodal Attention Alignment (U-MAA), a contrastive self-supervised mechanism integrated into the attention layers to align heterogeneous modalities without pixel-level correspondence or labels. L-MCAT achieves 95.4% overall accuracy on the SEN12MS dataset using only 20 labels per class, outperforming state-of-the-art baselines while using 47x fewer parameters and 23x fewer FLOPs than MCTrans. It maintains over 92% accuracy even under 50% spatial misalignment, demonstrating robustness for real-world deployment. The model trains end-to-end in under 5 hours on a single consumer GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20259
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle L-MCAT: Unpaired Multimodal Transformer with Contrastive Attention for Label-Efficient Satellite Image Classification
Goswami, Mitul
Goswami, Mrinal
Computer Vision and Pattern Recognition
We propose the Lightweight Multimodal Contrastive Attention Transformer (L-MCAT), a novel transformer-based framework for label-efficient remote sensing image classification using unpaired multimodal satellite data. L-MCAT introduces two core innovations: (1) Modality-Spectral Adapters (MSA) that compress high-dimensional sensor inputs into a unified embedding space, and (2) Unpaired Multimodal Attention Alignment (U-MAA), a contrastive self-supervised mechanism integrated into the attention layers to align heterogeneous modalities without pixel-level correspondence or labels. L-MCAT achieves 95.4% overall accuracy on the SEN12MS dataset using only 20 labels per class, outperforming state-of-the-art baselines while using 47x fewer parameters and 23x fewer FLOPs than MCTrans. It maintains over 92% accuracy even under 50% spatial misalignment, demonstrating robustness for real-world deployment. The model trains end-to-end in under 5 hours on a single consumer GPU.
title L-MCAT: Unpaired Multimodal Transformer with Contrastive Attention for Label-Efficient Satellite Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.20259