Hiracam Preserving Finegrained Spatial Relevance In Gradientbased Visual Explanations

# HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations

**arXiv ID:** 2608.19407
**Authors:** Manasi Nerurkar, Ali A. Minai
**Published:** 2026-08-19T19:44:43Z
**Abstract:**
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.

## Skill Description

This skill is generated from the arXiv paper: HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations (2608.19407).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2608.19407](http://arxiv.org/abs/2608.19407v1)