VLM-PL：通过视觉-语言模型实现类别增量目标检测的先进伪标签方法
VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model
AI总结：
针对类别增量目标检测中的伪标签遗忘问题，本文提出VLM-PL，利用视觉-语言模型和提示查询验证并精炼伪标签，融合新旧知识，在Pascal VOC与MS COCO上达到最先进性能。
摘要：
在类别增量目标检测（CIOD）领域，构建能够像人类一样持续学习的模型是一项重大挑战。伪标签方法虽然初期表现强大，但由于容易遗忘过去知识，在多场景增量学习中面临困难。为克服这一问题，我们提出一种名为视觉-语言模型辅助伪标签（Vision-Language Model assisted Pseudo-Labeling，VLM-PL）的新方法。该技术利用视觉-语言模型（VLM）验证伪真值（GT）的正确性，而无需额外的模型训练。VLM-PL首先从预训练检测器中获取伪GT。随后，我们使用精心设计的提示模板，结合图像和文本特征，为每个伪GT生成定制查询。这使VLM能够通过其响应判断正确性。此外，VLM-PL整合了来自后续训练的精炼伪GT和真实GT，有效结合新知识与旧知识。在Pascal VOC和MS COCO数据集上进行的大量实验，不仅凸显了VLM-PL在多场景中的卓越性能，也阐明了其在双场景中的有效性，并在两类场景中均取得了最先进结果。
英文摘要：
In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning due to their tendency to forget past knowledge. To overcome this, we introduce a new approach called Vision-Language Model assisted Pseudo-Labeling (VLM-PL). This technique uses Vision-Language Model (VLM) to verify the correctness of pseudo ground-truths (GTs) without requiring additional model training. VLM-PL starts by deriving pseudo GTs from a pre-trained detector. Then, we generate custom queries for each pseudo GT using carefully designed prompt templates that combine image and text features. This allows the VLM to classify the correctness through its responses. Furthermore, VLM-PL integrates refined pseudo and real GTs from upcoming training, effectively combining new and old knowledge. Extensive experiments conducted on the Pascal VOC and MS COCO datasets not only highlight VLM-PL's exceptional performance in multi-scenario but also illuminate its effectiveness in dual-scenario by achieving state-of-the-art results in both.
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。
