no code implementations • 29 Apr 2024 • Hanxiao Tan
Furthermore, we reveal that AM based on generative models fails the sanity checks and thus lack of fidelity.
1 code implementation • 26 Jan 2024 • Hanxiao Tan
In recent years, the performance of point cloud models has been rapidly improved.
no code implementations • 23 Feb 2023 • Hanxiao Tan
Due to the absence of ground truth, objective evaluation of explainability methods is an essential research direction.
no code implementations • 12 Apr 2022 • Hanxiao Tan
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.
2 code implementations • 17 Mar 2022 • Hanxiao Tan
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.
1 code implementation • 8 Oct 2021 • Hanxiao Tan, Helena Kotthaus
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.
1 code implementation • 28 Jul 2021 • Hanxiao Tan, Helena Kotthaus
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.
no code implementations • 21 May 2021 • Katharina Beckh, Sebastian Müller, Matthias Jakobs, Vanessa Toborek, Hanxiao Tan, Raphael Fischer, Pascal Welke, Sebastian Houben, Laura von Rueden
This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability.