Exploring specialization and sensitivity of convolutional neural networks under simultaneous image augmentations
stat.ML, cs.AI, cs.LG, cs.NA, math.NA
Submitted: 2025-03-05
Updated: 2026-11-07
Code: https://github.com/kharyuk/activation_sa
Terminology
Sources
- RISE: Randomized Input Sampling for Explanation of Black-box Models
- Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference