Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.
In- ternational journal of computer vision128, 336–359 (2020)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.
citing papers explorer
-
How to Evaluate and Refine your CAM
Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.
-
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.