arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.06484cs.CV
收藏

无实例领域自适应目标检测

Instance-Free Domain Adaptive Object Detection

School of Computer Science(计算机科学学院);Engineering, University of Electronic Science and Technology of China(电子科学与技术学院)

Hengfu Yu, Jinhong Deng, Lixin Duan, Wen Li

AI总结:

本文提出无实例领域自适应目标检测方法RSCN,通过背景特征原型对齐和关系一致性策略,在无目标实例情况下实现稳健适应,并在三个专门基准测试中取得优越性能。

摘要:

尽管领域自适应目标检测(DAOD)已取得显著进展,但大多数方法依赖于未标记的目标数据,假设其中包含足够的前景实例。然而,在许多实际场景(例如野生动物监控、病变检测)中,收集包含感兴趣对象的目标域数据成本高昂,而仅包含背景的数据却很丰富。这种常见的实际限制引入了显著的技术挑战:当目标实例不可用时,实现领域对齐的难度,迫使适应过程仅依赖目标背景信息。我们把这一挑战定义为新的问题:无实例领域自适应目标检测。为解决这一问题,我们提出了关系和结构一致性网络(RSCN),首次提出基于背景特征原型的对齐策略,同时在每个领域内鼓励源前景特征与背景特征之间的关系一致性,即使在没有目标实例的情况下也能实现稳健的适应。为了促进研究,我们进一步整理了三个专门的基准测试集,包括模拟自动驾驶检测、野生动物检测和肺结节检测。广泛的实验表明,RSCN在所有三个基准测试中在无实例场景下显著优于现有的DAOD方法。代码和基准测试将很快发布。

英文摘要:

While Domain Adaptive Object Detection (DAOD) has made significant strides, most methods rely on unlabeled target data that is assumed to contain sufficient foreground instances. However, in many practical scenarios (e.g., wildlife monitoring, lesion detection), collecting target domain data with objects of interest is prohibitively costly, whereas background-only data is abundant. This common practical constraint introduces a significant technical challenge: the difficulty of achieving domain alignment when target instances are unavailable, forcing adaptation to rely solely on the target background information. We formulate this challenge as the novel problem of Instance-Free Domain Adaptive Object Detection. To tackle this, we propose the Relational and Structural Consistency Network (RSCN) which pioneers an alignment strategy based on background feature prototypes while simultaneously encouraging consistency in the relationship between the source foreground features and the background features within each domain, enabling robust adaptation even without target instances. To facilitate research, we further curate three specialized benchmarks, including simulative auto-driving detection, wildlife detection, and lung nodule detection. Extensive experiments show that RSCN significantly outperforms existing DAOD methods across all three benchmarks in the instance-free scenario. The code and benchmarks will be released soon.

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。

↑