2022/05/22 by Mirtha Lucas, Miguel Lerma, Lucas, Mirtha +5 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #68T45 #Artificial Intelligence (cs.AI) #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #I.2.m #I.4.m #acm:68T45 #cs.AI #cs.CV #msc:68T45
paper · pdf · doi:10.48550/arxiv.2205.10900
16 pages, 33 figures
arxiv created 2022/05/22 · openalex publication_date 2022/05/22 · arxiv updated 2022/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural networks are becoming increasingly better at tasks that involve classifying and recognizing images. At the same time techniques intended to explain the network output have been proposed. One such technique is the Gradient-based Class Activation Map (Grad-CAM), which is able to locate features of an input image at various levels of a convolutional neural network (CNN), but is sensitive to the vanishing gradients problem. There are techniques such as Integrated Gradients (IG), that are not affected by that problem, but its use is limited to the input layer of a network. Here we introduce a new technique to produce visual explanations for the predictions of a CNN. Like Grad-CAM, our method can be applied to any layer of the network, and like Integrated Gradients it is not affected by the problem of vanishing gradients. For efficiency, gradient integration is performed numerically at the layer level using a Riemann-Stieltjes sum approximation. Compared to Grad-CAM, heatmaps produced by our algorithm are better focused in the areas of interest, and their numerical computation is more stable. Our code is available at https://github.com/mlerma54/RSIGradCAM