AWhat changed
Uses pooled class gradients to weight convolutional feature maps and produces a rectified localization map without changing or retraining the target CNN; Guided Grad-CAM combines it with a high-resolution backward visualization.
Scientific scope
Uses pooled class gradients to weight convolutional feature maps and produces a rectified localization map without changing or retraining the target CNN; Guided Grad-CAM combines it with a high-resolution backward visualization. Coarse first-order localization, not a complete causal explanation or proof of model fidelity. CAM is an inherited special case, apart from rectification/normalization; Guided Backprop and Grad-CAM are distinct components. V1 six-author order differs from2019v4; later added claims are not backdated.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Coarse first-order localization, not a complete causal explanation or proof of model fidelity. CAM is an inherited special case, apart from rectification/normalization; Guided Backprop and Grad-CAM are distinct components. V1 six-author order differs from2019v4; later added claims are not backdated.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction