Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-category objects as background, causing some proposals to be prematurely filtered out by the RPN while others are further misclassified by the RoI head. During testing, these proposals again receive low scores and are removed in post-processing, leading to a significant drop in recall and ultimately weakening novel-category detection performance.To address these issues, we propose a novel training framework-NoOVD-which innovatively integrates a self-distillation mechanism grounded in the knowledge of frozen vision-language models (VLMs). Specifically, we design K-FPN, which leverages the pretrained knowledge of VLMs to guide the model in discovering novel-category objects and facilitates knowledge distillation-without requiring additional data-thus preventing forced alignment of novel objects with background.Additionally, we introduce R-RPN, which adjusts the confidence scores of proposals during inference to improve the recall of novel-category objects. Cross-dataset evaluations on OV-LVIS, OV-COCO, and Objects365 demonstrate that our approach consistently achieves superior performance across multiple metrics.

翻译：尽管开放词汇目标检测（OVD）取得了显著进展，训练与测试阶段之间仍存在明显差距。在训练过程中，区域提议网络（RPN）和感兴趣区域（RoI）头部常将未标注的新类别目标错误分类为背景，导致部分提议被RPN过早过滤，其余提议则被RoI头部进一步误分类。在测试阶段，这些提议再次获得低分并在后处理中被剔除，造成召回率显著下降，最终削弱新类别检测性能。为解决这些问题，我们提出一种新颖的训练框架——NoOVD——其创新性地融合了基于冻结视觉语言模型（VLM）知识的自蒸馏机制。具体地，我们设计了K-FPN，利用VLM的预训练知识引导模型发现新类别目标，并促进知识蒸馏（无需额外数据），从而避免将新目标强制对齐为背景。此外，我们引入R-RPN，在推理过程中调整提议的置信度分数以提升新类别目标的召回率。在OV-LVIS、OV-COCO和Objects365上的跨数据集评估表明，我们的方法在多个指标上持续取得优异性能。