提升零样本组合识别能力，通过上下文提示和自适应对比学习增强属性与对象的关联理解。
Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training
- 利用已识别对象作为上下文线索，分步预测属性与对象以增强基础理解。
- 设计硬负样本生成与自适应损失调整的对比学习策略，强化属性-对象关联。
- 在三个基准数据集上实现跨封闭/开放世界场景的最优性能，适合零样本学习研究者。
组合零样本学习（CZSL）旨在识别未见过的属性与对象组合。现有基于CLIP的方法虽有进展，但因预训练机制固有局限，难以有效理解并关联属性与对象。为此，本文提出一种新框架ULAO，包含两个创新模块：理解属性与对象（UAO）模块通过分步预测及利用已识别对象作为上下文提示来改进基础理解；链接属性与对象（LAO）模块则引入定制化硬负样本生成与自适应损失调整的对比学习策略，以增强属性-对象关联。实验表明，该模型在三个基准数据集的封闭世界（CW）与开放世界（OW）场景中均达到领先性能。
原文摘要 · Abstract (English)
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of seen attributes and objects. Current CLIP-based methods in CZSL, despite their advancements, often fail to effectively understand and link the attributes and objects due to inherent limitations in CLIP's pretraining mechanisms. To address these shortcomings, this paper introduces a novel framework, Understanding and Linking Attributes and Objects (ULAO) in CZSL, which comprises two innovative modules. The Understanding Attributes and Objects (UAO) module improves primitive understanding by sequential primitive prediction and leveraging recognized objects as contextual hints for attribute classification. Concurrently, the Linking Attributes and Objects (LAO) module improves the attribute-object linkage understanding through a new contrastive learning strategy that incorporates tailored hard negative generation and adaptive loss adjustments. We demonstrate our model's superiority by showcasing its state-of-the-art performance across three benchmark datasets in both Closed-World (CW) and Open-World (OW) scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。