ViTPrompt：面向开放词表检测的免训练视觉 token 提示词精炼
ViTPrompt: Training-Free Prompt Refinement with Visual Tokens for Open-Vocabulary Detection
提出一种无需训练、无需反向传播的测试时提示词精炼方法：利用首轮高置信检测结果提取实例感知视觉 token 来增强文本提示词，再通过跨模态解码器进行第二轮推理，同时提升边界框定位与分类置信度，可直接用于开放词表检测器的分布偏移场景。
原文依据 augment the original text prompt with instance-aware visual tokens extracted from high-confidence detections in an initial forward pass
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论测试时自适应目标检测（TTAOD）旨在不重新训练的情况下，在分布偏移下维持检测性能。尽管近期视觉语言模型使开放词表检测成为可能，但现有的 TTAOD 方法——无论是闭集还是开放词表——都只专注于提升分类置信度，而很大程度上忽略了边界框定位的退化。为填补这一关键空白，我们提出 ViTPrompt（视觉 token 提示），一个免训练框架，在测试时联合精炼边界框与类别分数。我们的关键洞见是：在初始前向传播中，从高置信度检测结果中提取实例感知视觉 token 来增强原始文本提示词；随后在第二推理阶段使用该增强提示词，跨模态解码器利用增强的语义上下文生成更准确的框坐标与分类 logits。ViTPrompt 无需反向传播、参数更新或外部记忆，因而对实时部署极为高效。在多个分布外基准上的实验表明，ViTPrompt 达到最优性能，在定位精度与分类保真度上均带来一致提升，确立了其作为开放词表 TTAOD 整体解决方案的地位。
英文原文摘要 1341 字符
Test-Time Adaptive Object Detection (TTAOD) aims to maintain detection performance under distribution shifts without retraining. While recent vision-language models enable open-vocabulary detection, existing TTAOD methods--whether closed-set or open-vocabulary--focus exclusively on improving classification confidence and largely overlook the degradation of bounding box localization. To address this critical gap, we propose ViTPrompt (Visual Token-Prompting), a training-free framework that jointly refines both bounding boxes and class scores at test time. Our key insight is to augment the original text prompt with instance-aware visual tokens extracted from high-confidence detections in an initial forward pass; this enriched prompt is then used in a second inference stage, where the cross-modal decoder leverages the enhanced semantic context to produce more accurate box coordinates and classification logits. ViTPrompt requires no backpropagation, parameter updates, or external memory, making it highly efficient for real-time deployment. Experiments on multiple out-of-distribution benchmarks demonstrate that ViTPrompt achieves state-of-the-art performance, delivering consistent improvements in both localization accuracy and classification fidelity , and establishing itself as a holistic solution for open-vocabulary TTAOD.