论文信息 - Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task

Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task

In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them. We evaluate them on two criteria, the improvement of the network's core performance and the trust they are able to generate for users of the system. We find that in general, Grad-CAM seems to outperform LIME on this specific task: it yields more detailed insight from the point of view of core performance and 80\% of respondents asked to choose between them when it comes to the trust they inspire in the model choose Grad-CAM. However, we also posit that it is more useful to employ these two methods together, as the insights they yield are complementary.

[1] Zachary Chase Lipton. The mythos of model interpretability , 2016, ACM Queue.

[2] Klaus-Robert Müller,et al. Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[3] Abhishek Das,et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[4] Geoffrey E. Hinton,et al. ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5] Lalana Kagal,et al. Explaining Explanations: An Overview of Interpretability of Machine Learning , 2018, 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).

[6] Carlos Guestrin,et al. "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[7] Been Kim,et al. Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[8] Stefano Soatto,et al. Quick Shift and Kernel Methods for Mode Seeking , 2008, ECCV.

[9] Bolei Zhou,et al. Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).