mlsanityData to 14 Oct 2026

A matter of attitude: Focusing on positive and active gradients to boost saliency maps

arXiv 2309.12913 ↗First posted 22 Sep 2023cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Saliency maps have become one of the most widely used interpretability techniques for convolutional neural networks (CNN) due to their simplicity and the quality of the insights they provide. However, there are still some doubts about whether these insights are a trustworthy representation of what CNNs use to come up with their predictions. This paper explores how rescuing the sign of the gradients from the saliency map can lead to a deeper understanding of multi-class classification problems. Using both pretrained and trained from scratch CNNs we unveil that considering the sign and the effect not only of the correct class, but also the influence of the other classes, allows to better identify the pixels of the image that the network is really focusing on. Furthermore, how occluding or altering those pixels is expected to affect the outcome also becomes clearer.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 22 Sep 2023.

Builds on

15 of 24 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2022A ConvNet for the 2020scited by 3,579
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  8. 2018Sanity Checks for Saliency Mapscited by 1,156
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  10. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  11. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  12. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
3 more
  1. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  2. 2014Object Detectors Emerge in Deep Scene CNNscited by 179
  3. 2019Interpretable CNNs for Object Classificationcited by 17

Built on by

Not cited yet.