mlsanityData to 14 Oct 2026

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

arXiv 2306.13197 ↗First posted 22 Jun 2023cs.LG cs.AIcited by 3

Not on the map. Why?

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.

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

6 of 8 references.

References · 6

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  5. 2022Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradientscited by 5
  6. 2022Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localizationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2024Benchmarking the Attribution Quality of Vision Modelscited by 8
  2. 2025CAMs as Shapley Value-based Explainerscited by 5
  3. 2023A Vulnerability of Attribution Methods Using Pre-Softmax Scorescited by 0