Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples. Standard CZSL either identifies visual primitives or enhances unseen composed entities, and as a result, entanglement between state and object primitives cannot be fully utilized. Admittedly, vision-language models (VLMs) could naturally cope with CZSL through tuning prompts, while uneven entanglement leads prompts to be dragged into local optimum. In this paper, we take a further step to introduce a novel Disentangled and Recurrent Prompt Tuning framework termed DRPT to better tap the potential of VLMs in CZSL. Specifically, the state and object primitives are deemed as learnable tokens of vocabulary embedded in prompts and tuned on seen compositions. Instead of jointly tuning state and object, we devise a disentangled and recurrent tuning strategy to suppress the traction force caused by entanglement and gradually optimize the token parameters, leading to a better prompt space. Notably, we develop a progressive fine-tuning procedure that allows for incremental updates to the prompts, optimizing the object first, then the state, and vice versa. Meanwhile, the optimization of state and object is independent, thus clearer features can be learned to further alleviate the issue of entangling misleading optimization. Moreover, we quantify and analyze the entanglement in CZSL and supplement entanglement rebalancing optimization schemes. DRPT surpasses representative state-of-the-art methods on extensive benchmark datasets, demonstrating superiority in both accuracy and efficiency.

翻译：组合零样本学习（CZSL）旨在识别由已知知识组成的新颖概念，无需训练样本。标准CZSL方法要么识别视觉基元，要么增强未见的组合实体，导致状态基元与对象基元之间的纠缠无法被充分利用。诚然，视觉语言模型(VLMs)可通过提示调优自然应对CZSL任务，但非均匀纠缠会使提示陷入局部最优。本文进一步提出新型解耦与循环提示调优框架DRPT，以更充分挖掘VLMs在CZSL中的潜力。具体而言，我们将状态和对象基元视为嵌入提示中的词汇可学习令牌，并在可见组合上对其调优。与联合调优状态和对象不同，我们设计了解耦与循环调优策略，以抑制纠缠引起的牵引力并逐步优化令牌参数，从而构建更优的提示空间。值得注意的是，我们开发了渐进式微调流程，支持对提示进行增量更新：先优化对象再优化状态，或反向交替进行。同时，状态与对象的优化相互独立，因此可学习到更清晰的特征以进一步缓解误导性优化纠缠问题。此外，我们量化并分析了CZSL中的纠缠现象，补充了纠缠重平衡优化方案。DRPT在多个基准数据集上超越代表性最先进方法，展现出准确性与效率的双重优势。