跨域迁移检测知识，让模型在无标注数据下仍能识别新场景物体。
ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection
- 在预训练检测器的权重空间中建模知识迁移为几何运输问题。
- 在夜间、雾霾等极端条件下实现类级别知识的跨域传输。
- 适合缺乏标注数据的现实场景，如自动驾驶夜间检测。
尽管近期开放词汇目标检测架构（如 Grounding DINO）具备强大的零样本能力，但在领域偏移下性能显著下降。此外，许多实际应用场景（如夜间或雾天）缺乏大规模标注数据，难以直接微调。本文提出对齐基底重定位适应方法（ABRA），将有标注源域中的类别特异性检测知识迁移到无相关训练图像的目标域。ABRA 将这一适配过程建模为预训练检测器权重空间中的几何运输问题，通过对齐源域与目标域专家来实现类级别知识的转移。大量实验表明，ABRA 在多个严峻领域偏移下成功实现了类级专长的“传送”。代码将在论文被接受后公开。
原文摘要 · Abstract (English)
Although recent Open-Vocabulary Object Detection architectures, such as Grounding DINO, demonstrate strong zero-shot capabilities, their performance degrades significantly under domain shifts. Moreover, many domains of practical interest, such as nighttime or foggy scenes, lack large annotated datasets, preventing direct fine-tuning. In this paper, we introduce Aligned Basis Relocation for Adaptation(ABRA), a method that transfers class-specific detection knowledge from a labeled source domain to a target domain where no training images containing these classes are accessible. ABRA formulates this adaptation as a geometric transport problem in the weight space of a pretrained detector, aligning source and target domain experts to transport class-specific knowledge. Extensive experiments across challenging domain shifts demonstrate that ABRA successfully teleports class-level specialization under multiple adverse conditions. Our code will be made public upon acceptance.
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。