用于指代表达图像分割与定位的潜在表达生成
Latent Expression Generation for Referring Image Segmentation and Grounding
AI总结：
本文提出一种视觉定位框架，通过从单一文本生成多个融合互补视觉细节的潜在表达，并引入主体分配器、视觉概念注入器及正间隔对比学习，在RIS、REC和GRES任务上取得领先性能。
摘要：
视觉定位任务，如指代表达图像分割（RIS）和指代表达理解（REC），旨在根据给定的文本描述定位目标对象。图像中的目标对象可以通过多种方式进行描述，反映颜色、位置等多种不同属性。然而，现有大多数方法仅依赖单一的文本输入，只能捕捉视觉领域中丰富信息的一小部分。丰富的视觉细节与稀疏的文本线索之间的不匹配可能导致相似对象的错误识别。为解决这一问题，我们提出了一种新颖的视觉定位框架，该框架利用从单一文本输入生成的多个潜在表达，通过融入原始描述中缺失的互补视觉细节来增强定位能力。具体而言，我们引入了主体分配器和视觉概念注入器模块，将共享主体概念和不同属性概念嵌入到潜在表示中，从而捕捉独特的、针对目标对象的视觉线索。我们还提出了一种正间隔对比学习策略，使所有潜在表达与原始文本对齐，同时保留细微的变化。实验结果表明，我们的方法不仅在多个基准上超越了最先进的RIS和REC方法，而且在广义指代表达分割（GRES）基准上也取得了出色的性能。
英文摘要：
Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in multiple ways, reflecting diverse attributes such as color, position, and more. However, most existing methods rely on a single textual input, which captures only a fraction of the rich information available in the visual domain. This mismatch between rich visual details and sparse textual cues can lead to the misidentification of similar objects. To address this, we propose a novel visual grounding framework that leverages multiple latent expressions generated from a single textual input by incorporating complementary visual details absent from the original description. Specifically, we introduce subject distributor and visual concept injector modules to embed both shared-subject and distinct-attributes concepts into the latent representations, thereby capturing unique and target-specific visual cues. We also propose a positive-margin contrastive learning strategy to align all latent expressions with the original text while preserving subtle variations. Experimental results show that our method not only outperforms state-of-the-art RIS and REC approaches on multiple benchmarks but also achieves outstanding performance on the generalized referring expression segmentation (GRES) benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
