# Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation

arXiv: https://arxiv.org/abs/2603.17705 · HTML: https://mlsanity.com/paper/2603.17705/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 18 Mar 2026.

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

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data](https://mlsanity.com/paper/1904.00592/) (2019)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery](https://mlsanity.com/paper/2109.08937/) (2021)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review](https://mlsanity.com/paper/2205.01380/) (2022)
- [Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks](https://mlsanity.com/paper/1711.08681/) (2017)
- [A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images](https://mlsanity.com/paper/2104.12137/) (2021)
- [Crop mapping from image time series: deep learning with multi-scale label hierarchies](https://mlsanity.com/paper/2102.08820/) (2021)
- [Self-supervised Vision Transformers for Joint SAR-optical Representation Learning](https://mlsanity.com/paper/2204.05381/) (2022)
- [Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images](https://mlsanity.com/paper/2011.14302/) (2020)
- [Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network](https://mlsanity.com/paper/1807.11236/) (2018)
- [Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks](https://mlsanity.com/paper/1608.00775/) (2016)
- [Improving Multimodal Learning via Imbalanced Learning](https://mlsanity.com/paper/2507.10203/) (2025)
- [A Unified Framework with Multimodal Fine-tuning for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2410.11160/) (2024)
- [High-Resolution Semantic Labeling with Convolutional Neural Networks](https://mlsanity.com/paper/1611.01962/) (2016)
- [Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization](https://mlsanity.com/paper/2505.06635/) (2025)
- [An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2105.04132/) (2021)
- [Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2411.13127/) (2024)
- [Imbalance Knowledge-Driven Multi-modal Network for Land-Cover Semantic Segmentation Using Images and LiDAR Point Clouds](https://mlsanity.com/paper/2303.15777/) (2023)

## Abstract (arXiv)

Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose representations, adapting them to multimodal tasks often incurs substantial computational overhead and is prone to modality imbalance, where the contribution of auxiliary modalities is suppressed during optimization. To address these challenges, we propose MoBaNet, a parameter-efficient and modality-balanced symmetric fusion framework. Built upon a largely frozen VFM backbone, MoBaNet adopts a symmetric dual-stream architecture to preserve generalizable representations while minimizing the number of trainable parameters. Specifically, we design a Cross-modal Prompt-Injected Adapter (CPIA) to enable deep semantic interaction by generating shared prompts and injecting them into bottleneck adapters under the frozen backbone. To obtain compact and discriminative multimodal representations for decoding, we further introduce a Difference-Guided Gated Fusion Module (DGFM), which adaptively fuses paired stage features by explicitly leveraging cross-modal discrepancy to guide feature selection. Furthermore, we propose a Modality-Conditional Random Masking (MCRM) strategy to mitigate modality imbalance by masking one modality only during training and imposing hard-pixel auxiliary supervision on modality-specific branches. Extensive experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MoBaNet achieves state-of-the-art performance with significantly fewer trainable parameters than full fine-tuning, validating its effectiveness for robust and balanced multimodal fusion. The source code in this work is available at https://github.com/sauryeo/MoBaNet.