Tag: Grad-CAM

Researchers have unveiled a weakly supervised AI framework that segments crops, weeds and soil from image-level labels alone, achieving 76.04 ...

A new fairness-regularized framework called CoR-Hate retrieves real counterfactual examples from corpus data to reduce identity bias in hate-speech detection ...

A new study shows that popular AI explanation methods produce nearly identical heatmaps for different class labels, and introduces CASE, ...

Researchers in China have unveiled SpecMamba-Net, a dual-branch Mamba-based AI that fuses frequency-domain texture cues with linear-complexity global state-space modeling ...

A new federated learning framework lets hospitals train chest X-ray diagnostic AI collaboratively without sharing patient data, and it outperforms ...

A new study combines transfer learning, quantitative explainable AI, and drone-based tile-grid spray mapping to target pesticide application in pepper, ...

A multi-view deep learning framework can objectively recognize clinically defined mutual eye contact between children and assessors during naturalistic free ...

A new baseline study shows that deep learning can learn meaningful microstructural information from severely imbalanced ultra-high carbon steel images, ...

Researchers have developed a dual-path attention-augmented ResNet that recognizes radar jamming signals with 97.07 percent accuracy even at jamming-to-noise ratios ...

Researchers have developed a compact four-block residual attention network that classifies Alzheimer's disease and brain tumors from MRI scans with ...