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.

翻译：在类增量目标检测（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。伪标注方法尽管初期表现强大，但由于其易于遗忘过往知识的特性，在处理多场景增量学习时面临困难。为克服此局限，我们提出了一种名为视觉-语言模型辅助伪标注（VLM-PL）的新方法。该技术利用视觉-语言模型（VLM）验证伪真实标注（GTs）的正确性，无需额外模型训练。VLM-PL首先从预训练检测器中获取伪GTs，随后通过精心设计的提示模板为每个伪GT生成定制查询，该模板融合图像与文本特征，从而使VLM能依据其响应判断正确性。此外，VLM-PL整合了后续训练中经修正的伪GTs与真实GTs，有效融合新旧知识。在Pascal VOC和MS COCO数据集上的大量实验不仅凸显了VLM-PL在多场景下的卓越性能，还通过实现双场景下的最先进结果验证了其有效性。