Tag: Grad-CAM

A hybrid deep-learning model combining ConvNeXt and Swin Transformer architectures demonstrated 95.0 percent nine-class accuracy for diagnosing lumbar disc herniation ...

A systematic audit of a widely used ultrasound archive reveals that top-performing federated deep learning models classify polycystic ovary syndrome ...

A comparative study demonstrates that hybrid machine learning classifiers match end-to-end deep learning on saturated steel defect benchmarks but diverge ...

Researchers have developed MGTF-Net, a multi-backbone transformer fusion network that achieved 98.73 percent accuracy in classifying diseases across mango and ...

An attention-enhanced ResNet-50 deep learning model achieved an accuracy of 0.833 and an area under the curve of 0.855 when ...

Researchers have developed FMC-Net, a lightweight multi-branch convolutional neural network that improves fracture classification across multiple radiograph datasets by integrating ...

Researchers developed a Newtonian physics-inspired particle swarm optimization framework that tuned lightweight transfer learning models to classify five diabetic retinopathy ...

A deep learning framework that decodes spatial intratumor heterogeneity from preoperative computed tomography scans predicts cervical lymph node metastasis and ...

A novel explainable Vision Transformer framework integrating paired mammographic views achieved high diagnostic classification accuracy and superior explanation faithfulness across ...

Unsupervised computer vision analysis of street-level images from Seoul's illegal dumping monitoring locations identified three recurring landscape patterns, validated moderately ...