Search Results for author:
Found 3 papers, 1 papers with code
ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformer
Our proposed method provides an efficient and easy-to-implement alternative for generating visual explanations, without requiring attention and gradient information, which can be beneficial for various applications in the field of computer vision.
Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networks
To overcome this issue, Score-CAM and Ablation-CAM have been proposed as gradient-free methods, but they have longer execution times compared to CAM or Grad-CAM based methods, making them unsuitable for real-world solution though they resolved gradient related issues and enabled inference mode XAI.
Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selection
While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift happens.
