超越名词概念学习伪标签器用于开放词汇目标检测
Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection
AI总结：
本文提出PLAC方法，通过直接学习任意概念的区域-文本对齐生成伪标签，解决了OVOD中间接监督和概念迁移受限的问题，在OVOD和指代表达理解基准上均取得优异性能。
摘要：
开放词汇目标检测（OVOD）作为实现类人视觉智能的关键一步，近期受到了广泛关注。现有的OVOD方法通过将视觉-语言预训练模型中的任意概念知识迁移到检测器，将目标词汇从预定义类别扩展到开放世界。尽管先前方法取得了显著成功，但它们存在间接监督或可迁移概念有限的问题。在本文中，我们提出了一种简单而有效的方法，直接学习任意概念的区域-文本对齐。具体而言，所提方法旨在学习任意图像到文本的映射，用于任意概念的伪标签生成，命名为任意概念伪标签生成（PLAC）。所提方法在名词概念的标准OVOD基准上表现出具有竞争力的性能，并在任意概念的指代表达理解基准上取得了大幅提升。
英文摘要：
Open-vocabulary object detection (OVOD) has recently gained significant attention as a crucial step toward achieving human-like visual intelligence. Existing OVOD methods extend target vocabulary from pre-defined categories to open-world by transferring knowledge of arbitrary concepts from vision-language pre-training models to the detectors. While previous methods have shown remarkable successes, they suffer from indirect supervision or limited transferable concepts. In this paper, we propose a simple yet effective method to directly learn region-text alignment for arbitrary concepts. Specifically, the proposed method aims to learn arbitrary image-to-text mapping for pseudo-labeling of arbitrary concepts, named Pseudo-Labeling for Arbitrary Concepts (PLAC). The proposed method shows competitive performance on the standard OVOD benchmark for noun concepts and a large improvement on referring expression comprehension benchmark for arbitrary concepts.
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。
