基于提示的持续组成零样本学习
Prompt-Based Continual Compositional Zero-Shot Learning
AI总结：
PromptCCZSL通过多教师蒸馏和正交投影损失，实现持续组成零样本学习中的知识保留与泛化提升。
摘要：
我们针对视觉-语言模型在新属性、对象及其组合上的持续适应问题，解决组成零样本学习（CZSL）中的持续学习问题，同时防止遗忘先前知识。与经典持续学习不同，CCZSL更为复杂，因为属性和对象可能在不同会话中重复出现，而组合则保持唯一。基于冻结的VLM主干网络，我们提出了首个基于提示的持续组成零样本学习（PromptCCZSL）框架，通过近期加权多教师蒸馏保留先前知识。它采用会话感知的组成提示融合多模态特征以处理新组合，同时属性和对象提示通过会话无关融合学习以维持全局语义一致性，进一步通过余弦锚点损失（CAL）稳定化以保留先前知识。为增强当前会话的适应能力，正交投影损失（OPL）确保新属性和对象嵌入与先前嵌入保持不同，防止重叠，同时会话内多样性损失（IDL）促进当前会话嵌入之间的变化，以获得更丰富、更具判别性的表示。我们还引入了一个综合协议，联合衡量灾难性遗忘和组合泛化。在UT-Zappos和C-GQA基准上的广泛实验表明，PromptCCZSL在先前VLM和非VLM基线之上取得了显著改进，为闭合世界下的CCZSL设定了新基准。
英文摘要：
We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while preventing forgetting of prior knowledge. Unlike classical continual learning where classes are disjoint, CCZSL is more complex as attributes and objects may reoccur across sessions while compositions remain unique. Built on a frozen VLM backbone, we propose the first Prompt-based Continual Compositional Zero-Shot Learning (PromptCCZSL) framework that retains prior knowledge through recency-weighted multi-teacher distillation. It employs session-aware compositional prompts to fuse multimodal features for new compositions, while attribute and object prompts are learned through session-agnostic fusion to maintain global semantic consistency, which is further stabilized by a Cosine Anchor Loss (CAL) to preserve prior knowledge. To enhance adaptation in the current session, an Orthogonal Projection Loss (OPL) ensures that new attribute and object embeddings remain distinct from previous ones, preventing overlap, while an Intra-Session Diversity Loss (IDL) promotes variation among current-session embeddings for richer, more discriminative representations. We also introduce a comprehensive protocol that jointly measures catastrophic forgetting and compositional generalization. Extensive experiments on UT-Zappos and C-GQA benchmarks demonstrate that PromptCCZSL achieves substantial improvements over prior VLM-based and non-VLM baselines, setting a new benchmark for CCZSL in closed-world settings.
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。
