# PointCloud Saliency Maps

arXiv: https://arxiv.org/abs/1812.01687 · HTML: https://mlsanity.com/paper/1812.01687/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 30 of 112)

- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [Shape-invariant 3D Adversarial Point Clouds](https://mlsanity.com/paper/2203.04041/) (2022)
- [PointGuard: Provably Robust 3D Point Cloud Classification](https://mlsanity.com/paper/2103.03046/) (2021)
- [Object pop-up: Can we infer 3D objects and their poses from human interactions alone?](https://mlsanity.com/paper/2306.00777/) (2023)
- [Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification](https://mlsanity.com/paper/2111.10990/) (2021)
- [PointBA: Towards Backdoor Attacks in 3D Point Cloud](https://mlsanity.com/paper/2103.16074/) (2021)
- [3D Adversarial Attacks Beyond Point Cloud](https://mlsanity.com/paper/2104.12146/) (2021)
- [Isometric 3D Adversarial Examples in the Physical World](https://mlsanity.com/paper/2210.15291/) (2022)
- [Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds](https://mlsanity.com/paper/2403.05247/) (2024)
- [Physical-World Optical Adversarial Attacks on 3D Face Recognition](https://mlsanity.com/paper/2205.13412/) (2022)
- [A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks](https://mlsanity.com/paper/2212.10230/) (2022)
- [Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks](https://mlsanity.com/paper/2202.07261/) (2022)
- [A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks](https://mlsanity.com/paper/2310.00633/) (2023)
- [Surrogate Model-Based Explainability Methods for Point Cloud NNs](https://mlsanity.com/paper/2107.13459/) (2021)
- [Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients](https://mlsanity.com/paper/2203.15245/) (2022)
- [Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing](https://mlsanity.com/paper/2207.13326/) (2022)
- [PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition](https://mlsanity.com/paper/2208.09801/) (2022)
- [OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data](https://mlsanity.com/paper/2204.06577/) (2022)
- [Interpreting Representation Quality of DNNs for 3D Point Cloud Processing](https://mlsanity.com/paper/2111.03549/) (2021)
- [ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation](https://mlsanity.com/paper/2203.03888/) (2022)
- [SageMix: Saliency-Guided Mixup for Point Clouds](https://mlsanity.com/paper/2210.06944/) (2022)
- [LPF-Defense: 3D Adversarial Defense based on Frequency Analysis](https://mlsanity.com/paper/2202.11287/) (2022)
- [3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack](https://mlsanity.com/paper/2308.07546/) (2023)
- [Visualizing Global Explanations of Point Cloud DNNs](https://mlsanity.com/paper/2203.09505/) (2022)
- [Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion](https://mlsanity.com/paper/2211.16247/) (2022)
- [Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds](https://mlsanity.com/paper/2105.04839/) (2021)
- [Local Aggressive Adversarial Attacks on 3D Point Cloud](https://mlsanity.com/paper/2105.09090/) (2021)
- [Explainability-Aware One Point Attack for Point Cloud Neural Networks](https://mlsanity.com/paper/2110.04158/) (2021)
- [Invariance-Aware Randomized Smoothing Certificates](https://mlsanity.com/paper/2211.14207/) (2022)
- [Toward Availability Attacks in 3D Point Clouds](https://mlsanity.com/paper/2407.11011/) (2024)

## Abstract (arXiv)

3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise importance w.r.t.! classification performance, which is usually reflected by a saliency map. A saliency map is an important tool as it allows one to perform further processes on point-cloud data. In this paper, we propose a novel way of characterizing critical points and segments to build point-cloud saliency maps. Our method assigns each point a score reflecting its contribution to the model-recognition loss. The saliency map explicitly explains which points are the key for model recognition. Furthermore, aggregations of highly-scored points indicate important segments/subsets in a point-cloud. Our motivation for constructing a saliency map is by point dropping, which is a non-differentiable operator. To overcome this issue, we approximate point-dropping with a differentiable procedure of shifting points towards the cloud centroid. Consequently, each saliency score can be efficiently measured by the corresponding gradient of the loss w.r.t the point under the spherical coordinates. Extensive evaluations on several state-of-the-art point-cloud recognition models, including PointNet, PointNet++ and DGCNN, demonstrate the veracity and generality of our proposed saliency map. Code for experiments is released on urlhttps://github.com/tianzheng4/PointCloud-Saliency-Maps.