arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.00360cs.CVcs.LGstat.ML
收藏

图像分类中的偏差度量

Towards Measuring Bias in Image Classification

Fraunhofer IPA(弗劳恩霍夫生产技术与自动化研究所);CNR Institute of Applied Sciences and Intelligent Systems(意大利国家研究委员会应用科学与智能系统研究所);IDS Imaging Development Systems GmbH(IDS成像开发系统有限公司);University of Stuttgart(斯图加特大学)

Nina Schaaf, Omar de Mitri, Hang Beom Kim, Alexander Windberger, Marco F. Huber

摘要:

卷积神经网络(CNN)已经成为主要计算机视觉任务的最先进技术。然而,由于复杂的底层结构,它们的决定很难理解,这限制了它们在工业世界的某些环境中的使用。机器学习(ML)任务中一个常见且难以检测的挑战是数据偏差。在这项工作中,我们提出了一个系统的方法来发现数据偏见的归因图。为此,首先创建具有已知偏差的人工数据集,并用于训练有意偏置的CNN。然后使用属性图来检查网络的决策。最后,使用有意义的指标来衡量归因图相对于已知偏差的代表性。拟议的研究表明,一些归因图技术突出存在的偏见的数据比别人和指标可以支持偏见的识别。

英文摘要:

Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are hard to understand which limits their use in some context of the industrial world. A common and hard to detect challenge in machine learning (ML) tasks is data bias. In this work, we present a systematic approach to uncover data bias by means of attribution maps. For this purpose, first an artificial dataset with a known bias is created and used to train intentionally biased CNNs. The networks' decisions are then inspected using attribution maps. Finally, meaningful metrics are used to measure the attribution maps' representativeness with respect to the known bias. The proposed study shows that some attribution map techniques highlight the presence of bias in the data better than others and metrics can support the identification of bias.

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。

↑