OSLoPrompt: 弥合CLIP中的低监督挑战与开集域泛化之间的鸿沟
OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP
AI总结：
该研究提出小样本开集域泛化新范式及面向CLIP的OSLOPROMPT框架，通过域无关提示学习和伪开集样本训练专用提示两项创新，在五个基准上取得该任务新的最优性能。
摘要：
我们提出了小样本开集域泛化（LSOSDG）这一全新范式，将小样本学习与开集域泛化（ODG）相融合。尽管基于CLIP等模型的提示学习方法已推动域泛化（DG）取得进展，但它们在数据量极少的场景（如1样本）中表现不佳，且在检测与训练类别存在细粒度语义关联的开集样本时精度不足。为应对这些挑战，我们提出OSLOPROMPT——一种面向CLIP的先进提示学习框架，具备两项核心创新。首先，为应对源域监督有限的问题并提升域泛化效果，我们引入了一种域无关提示学习机制，该机制通过新型交叉注意力模块整合可适配的域特定线索与视觉引导的语义属性，同时辅以可学习的域通用及类别通用视觉提示，以增强跨模态适配性。其次，为提升推理阶段的异常值拒绝能力，我们将陌生样本归类为“未知”，并借助现成基础模型通过针对性查询策略系统生成的伪开集样本训练专用提示，这些伪样本与已知类别保持细粒度关联。该策略强化了特征学习，使我们的模型能更有效地检测不同粒度的开集样本。在五个基准上的广泛评估表明，OSLOPROMPT在LSOSDG任务上创下了新的最优性能，显著优于现有方法。
英文摘要：
We introduce Low-Shot Open-Set Domain Generalization (LSOSDG), a novel paradigm unifying low-shot learning with open-set domain generalization (ODG). While prompt-based methods using models like CLIP have advanced DG, they falter in low-data regimes (e.g., 1-shot) and lack precision in detecting open-set samples with fine-grained semantics related to training classes. To address these challenges, we propose OSLOPROMPT, an advanced prompt-learning framework for CLIP with two core innovations. First, to manage limited supervision across source domains and improve DG, we introduce a domain-agnostic prompt-learning mechanism that integrates adaptable domain-specific cues and visually guided semantic attributes through a novel cross-attention module, besides being supported by learnable domain- and class-generic visual prompts to enhance cross-modal adaptability. Second, to improve outlier rejection during inference, we classify unfamiliar samples as "unknown" and train specialized prompts with systematically synthesized pseudo-open samples that maintain fine-grained relationships to known classes, generated through a targeted query strategy with off-the-shelf foundation models. This strategy enhances feature learning, enabling our model to detect open samples with varied granularity more effectively. Extensive evaluations across five benchmarks demonstrate that OSLOPROMPT establishes a new state-of-the-art in LSOSDG, significantly outperforming existing methods.
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。
