Take 5：用少量特征实现可解释的图像分类
Take 5: Interpretable Image Classification with a Handful of Features
AI总结：
本文提出稀疏低维决策层模型SLDD-Model，仅用每类5个可解释特征即可在四个基准数据集上保持基线97%-100%的准确率，并设计损失函数提升特征多样性与精度。
摘要：
深度神经网络使用数千个大多难以理解的特征来识别单个类别，这种决策人类无法理解。我们提出在深度神经网络中构建一个可解释的稀疏低维最终决策层，并具备可衡量的可解释性，并在细粒度图像分类上进行了验证。我们认为，只有当特征本身可解释且单个决策仅使用极少数特征时，人类才能理解机器学习模型的决策。为此，最终层必须是稀疏的，并且为了使特征解释可行，还必须是低维的。我们将具有稀疏低维决策层的模型称为SLDD-Model。我们表明，与稠密高维决策层相比，SLDD-Model在局部和全局层面都更容易解释，同时能够保持有竞争力的准确率。此外，我们提出了一种损失函数，用于提升模型的特征多样性和准确率。我们更具可解释性的SLDD-Model每个类别仅使用50个特征中的5个，在四个常见基准数据集上与具有2048个特征的基线模型相比，保持了97%到100%的准确率。
英文摘要：
Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with measurable aspects of interpretability and demonstrate it on fine-grained image classification. We argue that a human can only understand the decision of a machine learning model, if the features are interpretable and only very few of them are used for a single decision. For that matter, the final layer has to be sparse and, to make interpreting the features feasible, low dimensional. We call a model with a Sparse Low-Dimensional Decision SLDD-Model. We show that a SLDD-Model is easier to interpret locally and globally than a dense high-dimensional decision layer while being able to maintain competitive accuracy. Additionally, we propose a loss function that improves a model's feature diversity and accuracy. Our more interpretable SLDD-Model only uses 5 out of just 50 features per class, while maintaining 97% to 100% of the accuracy on four common benchmark datasets compared to the baseline model with 2048 features.
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。
