提出DeMo框架，让多模态物体识别更精准。
DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification
- 分离多模态特征，保留各模态独特性
- 用注意力触发专家混合，动态融合特征
- 在三个数据集上表现领先，适合跨模态检索
多模态物体重识别旨在通过融合多源信息检索特定物体。现有方法多聚焦于异构特征的融合，但常忽略多模态成像中特征质量的动态变化，且模态间共享信息会削弱模态特异性。为此，本文提出一种新型特征学习框架DeMo，通过专家混合自适应平衡解耦特征。首先使用补丁集成特征提取器（PIFE）获取多粒度、多模态特征；随后引入分层解耦模块（HDM），将多模态特征解耦为非重叠形式，保留模态唯一性并提升特征多样性；最后设计注意力触发专家混合（ATMoE），以解耦特征生成的动态注意力权重替代传统门控机制。实验在三个多模态物体重识别基准上全面验证了方法的有效性，代码已开源。
原文摘要 · Abstract (English)
Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by combining complementary information from multiple modalities. Existing multi-modal object ReID methods primarily focus on the fusion of heterogeneous features. However, they often overlook the dynamic quality changes in multi-modal imaging. In addition, the shared information between different modalities can weaken modality-specific information. To address these issues, we propose a novel feature learning framework called DeMo for multi-modal object ReID, which adaptively balances decoupled features using a mixture of experts. To be specific, we first deploy a Patch-Integrated Feature Extractor (PIFE) to extract multi-granularity and multi-modal features. Then, we introduce a Hierarchical Decoupling Module (HDM) to decouple multi-modal features into non-overlapping forms, preserving the modality uniqueness and increasing the feature diversity. Finally, we propose an Attention-Triggered Mixture of Experts (ATMoE), which replaces traditional gating with dynamic attention weights derived from decoupled features. With these modules, our DeMo can generate more robust multi-modal features. Extensive experiments on three multi-modal object ReID benchmarks fully verify the effectiveness of our methods. The source code is available at https://github.com/924973292/DeMo.
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。