POGA：用于细粒度跨模态检索的释义与对立图对齐
POGA: Paraphrased and Oppositional Graph Alignment for Fine-Grained Cross-Modal Retrieval
POGA 将图像和文本解析为结构化图，并通过多源图增强生成释义正例和对抗负例，为跨模态细粒度对齐提供丰富的监督信号；其混合多粒度对齐目标（全局、节点、关系、焦点反驳）可复用于任何需要细粒度图文匹配的视觉语言任务。
原文依据 POGA comprises two core innovations: (1) Multi-source Graph Augmentation (MSGA), which not only generates paraphrased positives and oppositional negatives, but also parses the image and all text variants into structured graphs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大多数用于生成检索嵌入的模型并非为此目的而训练，这导致它们关注粗粒度语义对齐，而非特定的对象属性或排列。这限制了它们的性能，尤其是在跨模态细粒度检索等挑战性问题上。此外，它们的训练目标缺乏区分语义相似但事实不同的描述所需的判别能力。为应对这些挑战，我们提出了 POGA（释义与对立图对齐），一种用于细粒度跨模态对齐的新框架。POGA 包含两项核心创新：（1）多源图增强（MSGA），它不仅生成释义正例和对立负例，还将图像和所有文本变体解析为结构化图，以提供差异丰富的监督信号；（2）混合多粒度对齐（HMA），它定义了一个复合训练目标，在四个不同粒度上联合优化模型：包括稳健的双全局对齐，以及在节点、关系和焦点反驳三个细粒度层面上的精确匹配。在 DCI 和 DOCCI 等基准上的实验表明，POGA 在长文本理解和复杂关系判别方面优于多种最优方法。
英文原文摘要 1393 字符
Most of the models used to generate embeddings for retrieval are not trained for the purpose which leads them to focus on coarse semantic alignment rather than particular object attributes or arrangements. This limits their performance, particularly on challenging problems such as cross-modal fine-grained retrieval. Furthermore, their training objectives lack the discriminative ability required to distinguish between descriptions that are semantically similar but factually different. To address these challenges, we propose POGA (Paraphrased and Oppositional Graph Alignment), a novel framework for fine-grained cross-modal alignment. POGA comprises two core innovations: (1) Multi-source Graph Augmentation (MSGA), which not only generates paraphrased positives and oppositional negatives, but also parses the image and all text variants into structured graphs to provide difference-rich supervisory signals; (2) Hybrid Multi-granularity Alignment (HMA), which defines a composite training objective that jointly optimizes the model at four distinct granularities: including robust dual global alignment, and precise matching at three fine-grained levels: node, relation, and focal disproving. Experiments on benchmarks such as DCI and DOCCI demonstrate that POGA performs favorably against several state-of-the-art methods in long-text understanding and complex relation discrimination.