提出可自适应缺失模态的高效专家混合模型，提升遥感分类鲁棒性。
Rethinking Efficient Mixture-of-Experts for Remote Sensing Modality-Missing Classification
- 设计双路由机制，分离通用与模态感知专家，动态响应可用数据
- 在多个遥感数据集上实现95%以上准确率，计算开销仅增加2%
- 适用于遥感、自然图像等多场景，尤其适合传感器故障场景
多模态遥感分类常因传感器故障或环境干扰导致模态缺失，严重降低性能。本文从条件计算视角重新思考缺失模态学习，探究混合专家（MoE）模型是否能天然适应多种模态缺失情况。通过系统评估代表性MoE范式在不同缺失设置下的表现，揭示其潜力与局限。在此基础上，提出一种面向缺失感知的混合低秩适配器（MaMOL），一种参数高效的MoE框架，统一建模多种模态缺失情形。MaMOL引入双路由机制，解耦模态无关共享专家与模态感知动态专家，实现基于可用模态的自动专家激活。在多个遥感基准测试上，实验表明MaMOL在多样化缺失场景下显著提升鲁棒性与泛化能力，计算开销仅增加2%。自然图像数据集上的迁移实验进一步验证其可扩展性与跨域适用性。
原文摘要 · Abstract (English)
Multimodal remote sensing classification often suffers from missing modalities caused by sensor failures and environmental interference, leading to severe performance degradation. In this work, we rethink missing-modality learning from a conditional computation perspective and investigate whether Mixture-of-Experts (MoE) models can inherently adapt to diverse modality-missing scenarios. We first conduct a systematic study of representative MoE paradigms under various missing-modality settings, revealing both their potential and limitations. Building on these insights, we propose a Missing-aware Mixture-of-LoRAs (MaMOL), a parameter-efficient MoE framework that unifies multiple modality-missing cases within a single model. MaMOL introduces a dual-routing mechanism to decouple modality-invariant shared experts and modality-aware dynamic experts, enabling automatic expert activation conditioned on available modalities. Extensive experiments on multiple remote sensing benchmarks demonstrate that MaMOL significantly improves robustness and generalization under diverse missing-modality scenarios with minimal computational overhead. Transfer experiments on natural image datasets further validate its scalability and cross-domain applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。