Guided Grad-CAM
Algorithms AIMech:GuidedGradCAM DRAFT
A visualization method combining an upsampled Grad-CAM localization map with guided-backpropagation input-space scores.
Identity Notes & Concept Scope
Guided Grad-CAM is a specific fusion of two visualization methods, not a synonym for Grad-CAM or guided backpropagation alone.
Claims & Grounded Evidence
1 Claim
Mechanism
#explanation-method
Bilinearly resize the Grad-CAM map to input-image resolution, then multiply it pointwise with the guided-backpropagation visualization.
⚠️ Curated Limitations & Negative Results
- The output inherits dependence on the selected Grad-CAM layer and the guided-backpropagation rule.
- Higher image resolution and visual appeal do not establish universal explanation fidelity or causal importance.
Artificial Intelligence Ontology (AIO) Grounding
Mapped AIO Classes
| AIO Target Class | Mapping Relation | Mapping Rationale |
|---|---|---|
AIO:ArtificialNeuralNetwork
Artificial Neural Network
|
related_match | The fused visualization analyzes artificial-neural-network behavior through convolutional activations and backward input-space signals; it is an analysis method, not a network architecture. |
Evidence Sources & Primary Literature
1 Source| Source ID | Publication / Document | Type / Access | Reference & Checksum |
|---|---|---|---|
original-paper
|
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra
|
primary paper
full_text
|
sha256:fa3192ab0f81…
|
Curation Provenance
Curator: Codex
Method: ai_assisted
Model: GPT-6
Created: 2026-10-11T04:02:04Z
Updated: 2026-10-11T04:02:04Z
Source File:
data/curated/GuidedGradCAM.yaml