arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.06544cs.LG
收藏

多实例验证

Multiple Instance Verification

Department of Computer Science University of Waikato(计算机科学系 威基托大学)

Xin Xu, Eibe Frank, Geoffrey Holmes

AI总结:

针对多实例验证问题,提出交叉注意力池化(CAP)框架及两种新注意力函数,有效结合查询实例表示目标包,显著提升了验证准确率与关键实例识别能力。

摘要:

我们探索了多实例验证,这是一种将查询实例与具有异构且未知相关性的目标实例包进行验证的问题设置。我们表明,基于注意力的多实例学习(MIL)方法的朴素改编以及像孪生神经网络这样的标准验证方法不适用于此设置:直接结合最先进的(SOTA)MIL方法和孪生网络被证明并不比一个简单的基线模型更好,有时甚至显著更差。我们假设这可能是由于目标包的表示未能结合查询实例所致,因此引入了一种名为“交叉注意力池化”(CAP)的新池化方法。在CAP框架下,我们提出了两种新颖的注意力函数,以应对区分目标包中高度相似实例的挑战。通过对三个不同验证任务的实证研究,我们证明CAP在分类准确率和检测关键实例的能力方面,均以显著优势优于SOTA MIL方法的改编和基线模型。消融研究表明,识别关键实例的卓越能力归功于这些新的注意力函数。我们在 https://github.com/xxweka/MIV 分享了代码。

英文摘要:

We explore multiple instance verification, a problem setting in which a query instance is verified against a bag of target instances with heterogeneous, unknown relevancy. We show that naive adaptations of attention-based multiple instance learning (MIL) methods and standard verification methods like Siamese neural networks are unsuitable for this setting: directly combining state-of-the-art (SOTA) MIL methods and Siamese networks is shown to be no better, and sometimes significantly worse, than a simple baseline model. Postulating that this may be caused by the failure of the representation of the target bag to incorporate the query instance, we introduce a new pooling approach named "cross-attention pooling" (CAP). Under the CAP framework, we propose two novel attention functions to address the challenge of distinguishing between highly similar instances in a target bag. Through empirical studies on three different verification tasks, we demonstrate that CAP outperforms adaptations of SOTA MIL methods and the baseline by substantial margins, in terms of both classification accuracy and the ability to detect key instances. The superior ability to identify key instances is attributed to the new attention functions by ablation studies. We share our code at https://github.com/xxweka/MIV.

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。

↑