CAST：面向交互式文本到图像检索的上下文感知动态潜空间变换
CAST: Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrieval
提出一种轻量级即插即用的上下文感知潜空间变换模块（CASR），通过低秩投影和强度调制动态调整多模态嵌入空间，可复用于其他需要细粒度语义对齐的跨模态检索或生成任务。
原文依据 we propose Context-Aware Latent Space Transformation (CAST), a lightweight framework that dynamically transforms the common latent space of both textual and visual representations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论交互式文本到图像检索（I-TIR）旨在通过自然语言对话细化图像检索结果，使用户能够在多轮交互中逐步补充或修正搜索意图，从而获得更精确、更符合用户需求的视觉搜索体验。然而，现有方法在固定的多模态特征空间内进行跨模态检索，将所有对话文本和图像映射到同一个静态嵌入流形上。这种静态形式容易导致语义模糊，难以捕捉用户更新意图中的细微嵌入偏移，从而影响细粒度检索。为解决这一局限，我们提出了上下文感知潜空间变换（CAST），这是一个轻量级框架，能够根据具体演变的用户搜索意图，动态变换文本和视觉表示的公共潜空间，实现细粒度且自适应的语义对齐。CAST的核心是上下文感知空间调节器（CASR），这是一个关键的空间变换模块，由两个关键组件构成：（1）上下文感知低秩投影器（CLP），它学习基于意图上下文预测嵌入空间的投影方向；（2）上下文引导调制器（CGM），它自适应地确定合适的投影强度。CASR高度轻量，增加的参数和计算开销可忽略不计，并且可以无缝集成到多种I-TIR框架中。大量实验证明了我们所提出框架的有效性，表明它可以作为一种通用、即插即用的解决方案，用于高效且可扩展的交互式文本到图像检索。我们的源代码可在 https://github.com/HuiGuanLab/CAST 获取。
英文原文摘要 1765 字符
Interactive Text-to-Image Retrieval (I-TIR) aims to refine image retrieval results through natural language dialogues, which allows users to progressively supplement or correct their search intention across multiple rounds, enabling a more precise and user-aligned visual search experience.However, existing methods perform cross-modal retrieval within a fixed multimodal feature space, mapping all dialogue text and images onto the same static embedding manifold.Such static formulation easily causes semantic vagueness, making it difficult to capture subtle embedding shifts in the user's updated intention for fine-grained retrieval.To address this limitation, we propose Context-Aware Latent Space Transformation (CAST), a lightweight framework that dynamically transforms the common latent space of both textual and visual representations according to the specific evolving user's search intention, enabling fine-grained and adaptive semantic alignment.The core of CAST is the Context-Aware Space Regulator (CASR), a crucial space transformation module composed of two key components: (1) the Context-Aware Low-Rank Projector (CLP), which learns to predict the projection direction of embedding space based on the intent's context;and (2) the Context-Guided Modulator (CGM), which adaptively determines appropriate projection strength. CASR is highly lightweight, adding negligible parameters and computational overhead, and can be seamlessly integrated into diverse I-TIR frameworks.Extensive experiments demonstrate the effectiveness of our proposed framework, indicating that it can serve as a general, plug-and-play solution for efficient and scalable interactive text-to-image retrieval. Our source code is available at https://github.com/HuiGuanLab/CAST.