Search Results for author:
Found 8 papers, 4 papers with code
Flow AM: Generating Point Cloud Global Explanations by Latent Alignment
Furthermore, we reveal that AM based on generative models fails the sanity checks and thus lack of fidelity.
DAM: Diffusion Activation Maximization for 3D Global Explanations
In recent years, the performance of point cloud models has been rapidly improved.
The Generalizability of Explanations
Due to the absence of ground truth, objective evaluation of explainability methods is an essential research direction.
Maximum Entropy Baseline for Integrated Gradients
Integrated Gradients (IG), one of the most popular explainability methods available, still remains ambiguous in the selection of baseline, which may seriously impair the credibility of the explanations.
Visualizing Global Explanations of Point Cloud DNNs
In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors.
Explainability-Aware One Point Attack for Point Cloud Neural Networks
With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of point cloud networks by adversarial attacks.
Surrogate Model-Based Explainability Methods for Point Cloud NNs
In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors.
Explainable Machine Learning with Prior Knowledge: An Overview
This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability.
