For questions about the Gradient-weighted Class Activation Mapping (GradCAM) technique for explainable AI, which was proposed in the paper "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization" (2019) by Ramprasaath R. Selvaraju et al.
Questions tagged [grad-cam]
3 questions
3
votes
1 answer
In GradCAM, why is activation strength considered an indicator of relevant regions?
In the GradCAM paper section 3 they implicitly propose that two things are needed to understand which areas of an input image contribute most to the output class (in a multi-label classification problem). That is:
$A^k$ the final feature…
Alexander Soare
- 1,379
- 3
- 12
- 28
2
votes
1 answer
What does "aligned" across domains in domain adaptation?
within Delving into Local Features for Open-Set Domain Adaptation in Fundus Image Analysis paper. I got trouble in understanding their cluster-aware contrastive adaption $\mathcal{L}_\text{cca}$.
I don't get it how they defined "$i$ and $j$ are…
chickensoup
- 71
- 6
0
votes
0 answers
Grad cam on multi view cnn
I have two views of one object and using multi view cnn from .https://github.com/SAMY-ER/Multi-View-Image-Classification. This works great and I am getting better results. Though how can I apply grad cam to it. any help is appreciated . I want to…
user1631306
- 83
- 6