In this paper, we propose a CNN fine-tuning method which enables users to
give simultaneous feedback on two outputs: the classification itself and the
visual explanation for the classification. We present the effect of this
feedback strategy in a skin lesion classification task and measure how CNNs
react to the two types of user feedback. To implement this approach, we propose
a novel CNN architecture that integrates the Grad-CAM technique for explaining
the model's decision in the training loop. Using simulated user feedback, we
found that fine-tuning our model on both classification and explanation
improves visual explanation while preserving classification accuracy, thus
potentially increasing the trust of users in using CNN-based skin lesion
classifiers.

本文提出了一种卷积神经网络微调方法，利用用户反馈实现分类和可视化分类解释两方面输出的同时优化。将该方法应用于皮肤病分类任务，测试卷积神经网络对两种类型用户反馈的反应并说明该方法的作用，同时提出了一种新的卷积神经网络架构，该架构在训练循环中集成了 Grad-CAM 技术，以便解释模型的决策。通过模拟用户反馈，发现将分类和解释同时微调可以提高视觉解释效果，同时保留分类准确性，潜在地提高用户对于基于 CNN 的皮肤病分类器的信任。

基于皮肤病专家反馈的可解释卷积神经网络微调，提升分类可信度

Fine-tuning of explainable CNNs for skin lesion classification based on  dermatologists' feedback towards increasing trust

Deep neural network training spends most of the computation on examples that
are properly handled, and could be ignored. We propose to mitigate this
phenomenon with a principled importance sampling scheme that focuses
computation on "informative" examples, and reduces the variance of the
stochastic gradients during training. Our contribution is twofold: first, we
derive a tractable upper bound to the per-sample gradient norm, and second we
derive an estimator of the variance reduction achieved with importance
sampling, which enables us to switch it on when it will result in an actual
speedup. The resulting scheme can be used by changing a few lines of code in a
standard SGD procedure, and we demonstrate experimentally, on image
classification, CNN fine-tuning, and RNN training, that for a fixed wall-clock
time budget, it provides a reduction of the train losses of up to an order of
magnitude and a relative improvement of test errors between 5% and 17%.

本研究提出了一种基于重要性采样的计算优化方案，该方案能够减少深度神经网络训练过程中冗余计算，提升模型的训练效果并有效降低损失。实验结果显示，该方案能够在相同的时间预算下，将训练损失降低一个数量级，并提高测试误差 5％至 17％。