Abstract
Single-source Domain Generalized Object Detection (SDGOD), as a cutting-edge research topic in computer vision, aims to enhance model generalization capability in unseen target domains through single-source domain training. Current mainstream approaches attempt to mitigate domain discrepancies via data augmentation techniques. However, due to domain shift and limited domain-specific knowledge, models tend to fall into the pitfall of spurious correlations. This manifests as the model's over-reliance on simplistic classification features (e.g., color) rather than essential domain-invariant representations like object contours. To address this critical challenge, we propose the Cauvis (Causal Visual Prompts) method. First, we introduce a Cross-Attention Prompts module that mitigates bias from spurious features by integrating visual prompts with cross-attention. To address the inadequate domain knowledge coverage and spurious feature entanglement in visual prompts for single-domain generalization, we propose a dual-branch adapter that disentangles causal-spurious features while achieving domain adaptation via high-frequency feature extraction. Cauvis achieves state-of-the-art performance with 15.9-31.4% gains over existing domain generalization methods on SDGOD datasets, while exhibiting significant robustness advantages in complex interference environments.
Abstract (translated)
单一来源领域泛化目标检测（SDGOD）作为计算机视觉领域的前沿研究课题，旨在通过单源域训练来提升模型在未见目标域中的泛化能力。当前主流方法试图通过数据增强技术来缓解不同领域间的差异性问题。然而，由于领域偏移和特定领域知识的限制，模型容易陷入虚假相关性的陷阱中。这表现为模型过分依赖于简单的分类特征（例如颜色），而不是像物体轮廓这样的领域不变表示特征。 为了解决这一关键挑战，我们提出了Cauvis（因果视觉提示）方法。首先，我们引入了一个跨注意力提示模块，通过将视觉提示与跨注意力机制结合来减轻虚假特征偏差的影响。为了应对单域泛化中视觉提示的领域知识覆盖不足和虚假特征纠缠的问题，我们提出了一种双分支适配器，该适配器在提取高频特征实现领域适应的同时，还能分离因果虚假特征。 Cauvis 方法在 SDGOD 数据集上相对于现有领域的泛化方法取得了 15.9-31.4% 的性能提升，并且在复杂的干扰环境中展示了显著的鲁棒性优势。
URL
https://arxiv.org/abs/2510.19487
