提出FAR-Net模型，提升图像组合检索的语义对齐与融合效果。
FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval
- 分阶段融合：先细粒度对齐，再动态调整特征
- 在CIRR和FashionIQ上召回率提升2.4%和1.04%
- 适合需要精准图像修改的视觉语言任务
组合图像检索（CIR）是一种视觉语言任务，通过参考图像和修改文本检索目标图像，实现对期望变化的直观描述。现有方法多采用早期或晚期融合，前者过度关注文本显式细节而忽略视觉上下文，后者难以捕捉图像区域与文本标记间的细粒度语义对齐。为此，我们提出FAR-Net，一种包含增强语义对齐模块（ESAM）与自适应调和模块（ARM）的多阶段融合框架。ESAM采用基于交叉注意力的晚期融合以捕获细粒度语义关系，ARM则通过不确定性嵌入进行早期融合以提升鲁棒性与适应性。在CIRR和FashionIQ数据集上的实验表明，该方法相比现有最先进方法，召回率提升最高达2.4%（Recall@1）和1.04%（Recall@50），验证了FAR-Net在CIR任务中具有强鲁棒性与可扩展性。
原文摘要 · Abstract (English)
Composed image retrieval (CIR) is a vision language task that retrieves a target image using a reference image and modification text, enabling intuitive specification of desired changes. While effectively fusing visual and textual modalities is crucial, existing methods typically adopt either early or late fusion. Early fusion tends to excessively focus on explicitly mentioned textual details and neglect visual context, whereas late fusion struggles to capture fine-grained semantic alignments between image regions and textual tokens. To address these issues, we propose FAR-Net, a multi-stage fusion framework designed with enhanced semantic alignment and adaptive reconciliation, integrating two complementary modules. The enhanced semantic alignment module (ESAM) employs late fusion with cross-attention to capture fine-grained semantic relationships, while the adaptive reconciliation module (ARM) applies early fusion with uncertainty embeddings to enhance robustness and adaptability. Experiments on CIRR and FashionIQ show consistent performance gains, improving Recall@1 by up to 2.4% and Recall@50 by 1.04% over existing state-of-the-art methods, empirically demonstrating that FAR Net provides a robust and scalable solution to CIR tasks.
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。