发表机构
Korea University; Sungkyunkwan University; KT Corporation（高丽大学; 成均馆大学; KT公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出GRASP框架，通过挖掘视觉-文本概念并训练轻量级稀疏头，生成可解释的概念级证据以补充稠密语义匹配，在文本-图像检索中实现更优准确率与更紧凑接地的稀疏空间。
AI 中文摘要
跨模态检索已通过将图像和文本编码到共享稠密嵌入空间的视觉-语言预训练模型得到推进。虽然稠密表示能有效捕获整体语义相似性，但它们常常掩盖了精确跨模态匹配所需的细粒度视觉-文本信息。近期方法引入学习得到的稀疏分支，以词汇证据补充稠密匹配，但它们依赖冗余的语言模型词元空间，且缺乏对稀疏维度的显式接地。我们提出GRASP，一个紧凑且接地的稀疏学习框架，从语料库中挖掘视觉-文本概念。一个轻量级稀疏头被训练来预测与每个图像或文本相关的概念，产生可解释的概念级证据，以补充稠密语义匹配。大量实验表明，GRASP在检索准确性上优于最先进的稠密-稀疏基线，同时产生更紧凑且接地的稀疏空间。
英文摘要
Cross-modal retrieval has been advanced by vision-language pre-trained models that encode images and texts into a shared dense embedding space. While dense representations effectively capture overall semantic similarity, they often obscure fine-grained visual-textual information needed for precise cross-modal matching. Recent methods introduce a learned sparse branch to complement dense matching with lexical evidence, but they rely on a redundant language-model token space and lack explicit grounding for sparse dimensions. We propose GRASP, a compact and grounded sparse learning framework that mines visual-textual concepts from the corpus. A lightweight sparse head is trained to predict concepts relevant to each image or text, yielding interpretable concept-level evidence that complements dense semantic matching. Extensive experiments show that GRASP improves retrieval accuracy over the state-of-the-art dense-sparse baselines while yielding a more compact and grounded sparse space.
CommentsAccepted for oral presentation at KEIR@CIKM 2026
