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

2020/08/04 by David Cian, Cian, David, Jan van Gemert +3 · 1 citation
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2008.01584

openalex publication_date 2020/08/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Understanding plant phenotypes in crop breeding through explainable AI

Related

• Adapting Grad-CAM for Embedding Networks
• Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks
• Explaining decision of model from its prediction
• Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study\n with Biological Data
• Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification