Search papers, labs, and topics across Lattice.
This paper introduces HiRA-CAM, an enhanced method for generating saliency maps in convolutional neural networks (CNNs) that improves upon existing techniques like LayerCAM and Grad-CAM. By adaptively utilizing activation maps from all layers of the CNN, HiRA-CAM achieves a more precise representation of spatial relevance in visual explanations. The results demonstrate that HiRA-CAM significantly outperforms its predecessors in object classification tasks, highlighting its potential for enhancing interpretability in deep learning models.
HiRA-CAM achieves superior saliency maps by leveraging all layers of a CNN, revealing fine-grained spatial relevance that previous methods miss.
Deep Learning models can include billions of parameters or more, making it difficult to explain their internal transformations and outputs. However, explainability is increasing in importance due to the use of AI in crucial applications. This paper focuses on the interpretability of convolutional neural networks (CNNs). Building on the popular gradient based method LayerCAM for extracting internal features in CNNs, we propose an improved method named HiRA-CAM, and show that it outperforms both LayerCAM and Grad-CAM on creating useful saliency maps for object classification. The main feature of HiRA-CAM is its adaptive use of activation maps from all the layers of the CNN to arrive at a more focused saliency map.
