Goto

Collaborating Authors

 human-inspired explanation

Human-inspired Explanations for Vision Transformers and Convolutional Neural Networks

Panda, Mahadev Prasad, Tiezzi, Matteo, Vilas, Martina, Roig, Gemma, Eskofier, Bjoern M., Zanca, Dario

arXiv.org Artificial Intelligence

We introduce Foveation-based Explanations (FovEx), a novel human-inspired visual explainability (XAI) method for Deep Neural Networks. Our method achieves state-of-the-art performance on both transformer (on 4 out of 5 metrics) and convolutional models (on 3 out of 5 metrics), demonstrating its versatility. Furthermore, we show the alignment between the explanation map produced by FovEx and human gaze patterns (+14\% in NSS compared to RISE, +203\% in NSS compared to gradCAM), enhancing our confidence in FovEx's ability to close the interpretation gap between humans and machines.

  arxiv preprint arxiv, human-inspired explanation, proceedings, (9 more...)
2408.02123
  Country:
  Genre: Research Report (0.40)
  Technology:

Add feedback