arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.03094cs.CVcs.LG
收藏

通过增强的开集目标检测器实现跨域少样本目标检测

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

Fudan University(复旦大学);ETH Zürich(苏黎世联邦理工学院);INSAIT;Southeast University(东南大学);BOE Technology(京东方科技集团)

Yuqian Fu, Yu Wang, Yixuan Pan, Lian Huai, Xingyu Qiu, Zeyu Shangguan, Tong Liu, Yanwei Fu, Luc Van Gool, Xingqun Jiang

AI总结:

本文研究跨域少样本目标检测,通过建立CD-FSOD基准揭示现有开集检测器在跨域泛化上的不足,提出CD-ViTO模型,利用可学习实例特征、实例重加权和域提示器模块显著提升了跨域检测性能。

摘要:

本文研究具有挑战性的跨域少样本目标检测(CD-FSOD),旨在利用最少的标注样本为新颖领域开发准确的目标检测器。尽管基于Transformer的开集检测器(如DE-ViT)在传统少样本目标检测中展现出潜力,但它们在CD-FSOD中的泛化能力仍不明确:1)此类开集检测方法能否轻松泛化到CD-FSOD?2)若不能,面对巨大的领域差距时如何增强模型?为回答第一个问题,我们采用包括风格、类间方差(ICV)和不可定义边界(IB)在内的度量来理解领域差距。基于这些度量,我们建立了一个名为CD-FSOD的新基准来评估目标检测方法,揭示当前大多数方法无法跨域泛化。在技术上,我们观察到性能下降与提出的度量相关:风格、ICV和IB。因此,我们提出几个新颖模块来解决这些问题。首先,可学习的实例特征将初始固定实例与目标类别对齐,增强特征独特性。其次,实例重加权模块为具有轻微IB的高质量实例分配更高重要性。第三,域提示器通过合成不改变语义内容的虚拟域,鼓励特征对不同风格具有鲁棒性。这些技术共同促成了用于CD-FSOD的跨域视觉Transformer(CD-ViTO)的开发,在基础DE-ViT上取得显著提升。实验结果验证了我们模型的有效性。

英文摘要:

This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundaries (IB) to understand the domain gap. Based on these measures, we establish a new benchmark named CD-FSOD to evaluate object detection methods, revealing that most of the current approaches fail to generalize across domains. Technically, we observe that the performance decline is associated with our proposed measures: style, ICV, and IB. Consequently, we propose several novel modules to address these issues. First, the learnable instance features align initial fixed instances with target categories, enhancing feature distinctiveness. Second, the instance reweighting module assigns higher importance to high-quality instances with slight IB. Third, the domain prompter encourages features resilient to different styles by synthesizing imaginary domains without altering semantic contents. These techniques collectively contribute to the development of the Cross-Domain Vision Transformer for CD-FSOD (CD-ViTO), significantly improving upon the base DE-ViT. Experimental results validate the efficacy of our model.

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。

↑