arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.01440cs.LG
收藏

Memory Wrap:一种数据高效且可解释的图像分类模型扩展

Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models

Sapienza University of Rome(罗马第一大学);Sony AI(索尼人工智能)

Biagio La Rosa, Roberto Capobianco, Daniele Nardi

AI总结:

本文提出 Memory Wrap,一种通过内容注意力机制利用训练样本记忆的即插即用扩展,在提升图像分类模型数据效率的同时提供基于示例和反事实的可解释性。

摘要:

由于深度学习技术的黑箱特性和数据饥渴特性,其在医疗和司法等关键领域的实际应用尚未被广泛采用。本文提出了 Memory Wrap,一种可即插即用地扩展到任何图像分类模型的方案。Memory Wrap 通过采用输入与过去训练样本记忆之间的内容注意力机制,同时提升了数据效率和模型可解释性。我们表明,当从有限数据集学习时,Memory Wrap 优于标准分类器;当从完整数据集学习时,其性能达到可比水平。我们讨论了与标准分类器相比,其结构和内容注意力机制如何使预测具有可解释性。为此,我们既展示了一种基于记忆内容构建示例解释和反事实解释的方法,也展示了如何利用这些解释来洞察其决策过程。我们在三个不同数据集(即 CIFAR10、SVHN 和 CINIC10)上使用多种架构对图像分类任务进行了方法测试。

英文摘要:

Due to their black-box and data-hungry nature, deep learning techniques are not yet widely adopted for real-world applications in critical domains, like healthcare and justice. This paper presents Memory Wrap, a plug-and-play extension to any image classification model. Memory Wrap improves both data-efficiency and model interpretability, adopting a content-attention mechanism between the input and some memories of past training samples. We show that Memory Wrap outperforms standard classifiers when it learns from a limited set of data, and it reaches comparable performance when it learns from the full dataset. We discuss how its structure and content-attention mechanisms make predictions interpretable, compared to standard classifiers. To this end, we both show a method to build explanations by examples and counterfactuals, based on the memory content, and how to exploit them to get insights about its decision process. We test our approach on image classification tasks using several architectures on three different datasets, namely CIFAR10, SVHN, and CINIC10.

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。

↑