arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.08078cs.CV
收藏

Patchnet:用于图像分类的可解释神经网络

Patchnet: Interpretable Neural Networks for Image Classification

Massachusetts Institute of Technology(麻省理工学院)

Adityanarayanan Radhakrishnan, Charles Durham, Ali Soylemezoglu, Caroline Uhler

摘要:

了解复杂的机器学习模型如何做出分类决策对于其在医疗保健等敏感领域的接受至关重要。为此,我们提出了PatchNet,一种方法,它提供的功能指示图像中的每个类使用限制全局图像上下文和分类错误之间的权衡。我们对这种权衡进行了数学分析,展示了Patchnet构建学习特征的清晰视觉热图表示的能力,并通过将PatchNet应用于ISBI-ISIC 2017黑色素瘤分类挑战中的良性/恶性皮肤病变分类,将这些特征与领域专家选择的特征进行定量比较。

英文摘要:

Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care. Towards this end, we present PatchNet, a method that provides the features indicative of each class in an image using a tradeoff between restricting global image context and classification error. We mathematically analyze this tradeoff, demonstrate Patchnet's ability to construct sharp visual heatmap representations of the learned features, and quantitatively compare these features with features selected by domain experts by applying PatchNet to the classification of benign/malignant skin lesions from the ISBI-ISIC 2017 melanoma classification challenge.

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。

↑