Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Compositional Zero-Shot Learning (CZSL) mainly focus on image classification. This paper aims to enhance CZSL in object detection without forgetting prior learned knowledge. We use Grounding DINO and incorporate Compositional Soft Prompting (CSP) into it and extend it with Compositional Anticipation. We achieve a 70.5% improvement over CSP on the harmonic mean (HM) between seen and unseen compositions on the CLEVR dataset. Furthermore, we introduce Contrastive Prompt Tuning to incrementally address model confusion between similar compositions. We demonstrate the effectiveness of this method and achieve an increase of 14.5% in HM across the pretrain, increment, and unseen sets. Collectively, these methods provide a framework for learning various compositions with limited data, as well as improving the performance of underperforming compositions when additional data becomes available.

翻译：尽管计算机视觉模型已取得显著进展，但其对新颖物体-属性组合的泛化能力仍然有限。现有的组合零样本学习方法主要集中于图像分类任务。本文旨在增强目标检测中的组合零样本学习能力，同时避免遗忘已习得的知识。我们采用Grounding DINO模型，将组合软提示技术融入其中，并通过组合预见机制进行扩展。在CLEVR数据集上，我们在可见与不可见组合的调和平均值指标上实现了相较于组合软提示方法70.5%的性能提升。此外，我们提出对比提示调优方法，以渐进式缓解模型对相似组合的混淆问题。我们验证了该方法的有效性，在预训练集、增量集和不可见集的调和平均值上实现了14.5%的提升。总体而言，这些方法构建了一个能够利用有限数据学习多种组合的框架，并能在获得额外数据时提升欠佳组合的识别性能。