arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.05072cs.CV
收藏

不可见域中的Few-Shot目标检测

Few-Shot Object Detection in Unseen Domains

Robert Bosch Corporate Research(博世集团研究院);University Of Stuttgart(斯图加特大学);Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院);Fraunhofer IOSB(弗劳恩霍夫光电、系统技术与图像利用研究所)

Karim Guirguis, George Eskandar, Matthias Kayser, Bin Yang, Juergen Beyerer

摘要:

近年来,Few-Shot目标检测(FSOD)通过传递在丰富的基类上获得的知识来学习具有有限数据的新对象类而蓬勃发展。FSOD方法通常假设很少提供的新类的例子和测试时的数据属于同一个域。然而,这种假设在各种工业和机器人应用中并不成立,在这些应用中,模型可以从源域学习新的类,同时从目标域推断类。在这项工作中,我们解决的任务,zero-shot领域自适应,也被称为领域泛化,FSOD。具体来说,我们假设在训练过程中,目标域中的新类的图像和标签都不可用。我们解决域间隙的方法是双重的。首先,我们利用元训练范式,在这里我们学习基础类上的领域转移,然后将领域知识转移到新类。其次,我们提出了各种数据增强技术的几个镜头的新类,以占所有可能的特定领域的信息。为了约束网络只对领域不可知的类特定表示进行编码,提出了一种对比损失,以最大化前景建议和类嵌入之间的互信息,并减少网络对目标域背景信息的偏见。我们在T-LESS,PASCAL-VOC和ExDark数据集上的实验表明,所提出的方法成功地缓解了领域差距,而无需利用目标领域的新类别的标签或图像。

英文摘要:

Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples of novel classes and test-time data belong to the same domain. However, this assumption does not hold in various industrial and robotics applications, where a model can learn novel classes from a source domain while inferring on classes from a target domain. In this work, we address the task of zero-shot domain adaptation, also known as domain generalization, for FSOD. Specifically, we assume that neither images nor labels of the novel classes in the target domain are available during training. Our approach for solving the domain gap is two-fold. First, we leverage a meta-training paradigm, where we learn the domain shift on the base classes, then transfer the domain knowledge to the novel classes. Second, we propose various data augmentations techniques on the few shots of novel classes to account for all possible domain-specific information. To constraint the network into encoding domain-agnostic class-specific representations only, a contrastive loss is proposed to maximize the mutual information between foreground proposals and class embeddings and reduce the network's bias to the background information from target domain. Our experiments on the T-LESS, PASCAL-VOC, and ExDark datasets show that the proposed approach succeeds in alleviating the domain gap considerably without utilizing labels or images of novel categories from the target domain.

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。

↑