# Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?

arXiv: https://arxiv.org/abs/2306.13197 · HTML: https://mlsanity.com/paper/2306.13197/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 22 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients](https://mlsanity.com/paper/2205.10838/) (2022)
- [Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localization](https://mlsanity.com/paper/2205.10900/) (2022)

## Built on by (most cited first, 3 of 3)

- [Benchmarking the Attribution Quality of Vision Models](https://mlsanity.com/paper/2407.11910/) (2024)
- [CAMs as Shapley Value-based Explainers](https://mlsanity.com/paper/2501.06261/) (2025)
- [A Vulnerability of Attribution Methods Using Pre-Softmax Scores](https://mlsanity.com/paper/2307.03305/) (2023)

## Abstract (arXiv)

Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of pre-softmax scores versus post-softmax scores, and their respective advantages and disadvantages.