VK-Det: 基于视觉知识引导的开放词汇空域目标检测
VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection
AI总结：
VK-Det通过视觉知识引导的原型学习方法，无需额外监督实现开放词汇空域目标检测，取得优于现有方法的检测性能。
摘要：
为识别超出预定义类别的对象，开放词汇空域目标检测（OVAD）利用视觉-语言模型（VLMs）的零样本能力，从基础类别推广到新类别。现有方法通常利用自学习机制，通过弱文本监督生成区域级伪标签，以对齐检测器与VLMs的语义空间。然而，文本依赖性导致语义偏差，限制了开放词汇扩展到文本指定的概念。我们提出了VK-Det，一种无需额外监督的视觉知识引导的开放词汇目标检测框架。首先，我们发现并利用视觉编码器固有的信息区域感知能力，以实现细粒度定位和自适应蒸馏。其次，我们引入了一种新的原型感知伪标签策略。它通过特征聚类建模类间决策边界，并通过原型匹配将检测区域映射到潜在类别。这增强了对新对象的关注，同时补偿了缺失的监督。广泛的实验表明，该方法在DIOR上达到30.1 mAP^N，在DOTA上达到23.3 mAP^N，优于甚至额外监督的方法。
英文摘要：
To identify objects beyond predefined categories, open-vocabulary aerial object detection (OVAD) leverages the zero-shot capabilities of visual-language models (VLMs) to generalize from base to novel categories. Existing approaches typically utilize self-learning mechanisms with weak text supervision to generate region-level pseudo-labels to align detectors with VLMs semantic spaces. However, text dependence induces semantic bias, restricting open-vocabulary expansion to text-specified concepts. We propose $\textbf{VK-Det}$, a $\textbf{V}$isual $\textbf{K}$nowledge-guided open-vocabulary object $\textbf{Det}$ection framework $\textit{without}$ extra supervision. First, we discover and leverage vision encoder's inherent informative region perception to attain fine-grained localization and adaptive distillation. Second, we introduce a novel prototype-aware pseudo-labeling strategy. It models inter-class decision boundaries through feature clustering and maps detection regions to latent categories via prototype matching. This enhances attention to novel objects while compensating for missing supervision. Extensive experiments show state-of-the-art performance, achieving 30.1 $\mathrm{mAP}^{N}$ on DIOR and 23.3 $\mathrm{mAP}^{N}$ on DOTA, outperforming even extra supervised methods.
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。
