arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02112cs.LG
收藏

查找和修复虚假模式与简化

Finding and Fixing Spurious Patterns with Explanations

CMU(卡内基梅隆大学);Microsoft Research(微软研究院)

Gregory Plumb, Marco Tulio Ribeiro, Ameet Talwalkar

摘要:

图像分类器经常使用虚假模式,例如“依赖于人的存在来检测网球拍”,这并不普遍。在这项工作中,我们提出了一个端到端的管道,用于识别和减轻这种模型的虚假模式,假设我们可以访问像素的对象注释。我们从识别模式开始,例如“如果我们隐藏人,模型对网球拍的预测有63%的时间会发生变化。“然后,如果一个模式是虚假的,我们通过一种新形式的数据增强来减轻它。我们证明,我们的方法确定了一组不同的虚假模式,它减轻了他们通过产生一个模型,这是更准确的分布的虚假模式是没有帮助的,更强大的分布偏移。

英文摘要:

Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-end pipeline for identifying and mitigating spurious patterns for such models, under the assumption that we have access to pixel-wise object-annotations. We start by identifying patterns such as "the model's prediction for tennis racket changes 63% of the time if we hide the people." Then, if a pattern is spurious, we mitigate it via a novel form of data augmentation. We demonstrate that our method identifies a diverse set of spurious patterns and that it mitigates them by producing a model that is both more accurate on a distribution where the spurious pattern is not helpful and more robust to distribution shift.

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。

↑