Robustness Certification for Point Cloud Models
- URL: http://arxiv.org/abs/2103.16652v1
- Date: Tue, 30 Mar 2021 19:52:07 GMT
- Title: Robustness Certification for Point Cloud Models
- Authors: Tobias Lorenz, Anian Ruoss, Mislav Balunovi\'c, Gagandeep Singh,
Martin Vechev
- Abstract summary: We introduce 3DCertify, the first verifier able to certify robustness of point cloud models.
3DCertify is based on two key insights: (i) a generic relaxation based on first-order Taylor approximations, and (ii) a precise relaxation for global feature pooling.
We demonstrate the effectiveness of 3DCertify by performing an extensive evaluation on a wide range of 3D transformations.
- Score: 10.843109238068982
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The use of deep 3D point cloud models in safety-critical applications, such
as autonomous driving, dictates the need to certify the robustness of these
models to semantic transformations. This is technically challenging as it
requires a scalable verifier tailored to point cloud models that handles a wide
range of semantic 3D transformations. In this work, we address this challenge
and introduce 3DCertify, the first verifier able to certify robustness of point
cloud models. 3DCertify is based on two key insights: (i) a generic relaxation
based on first-order Taylor approximations, applicable to any differentiable
transformation, and (ii) a precise relaxation for global feature pooling, which
is more complex than pointwise activations (e.g., ReLU or sigmoid) but commonly
employed in point cloud models. We demonstrate the effectiveness of 3DCertify
by performing an extensive evaluation on a wide range of 3D transformations
(e.g., rotation, twisting) for both classification and part segmentation tasks.
For example, we can certify robustness against rotations by $\pm60^\circ$ for
95.7% of point clouds, and our max pool relaxation increases certification by
up to 15.6%.
Related papers
- CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation [33.07886526437753]
3D point clouds captured from real-world sensors frequently encompass noisy points due to various obstacles.
These challenges hinder the deployment of pre-trained point cloud recognition models trained on clean point clouds.
We propose CloudFixer, a test-time input adaptation method tailored for 3D point clouds.
arXiv Detail & Related papers (2024-07-23T05:35:04Z) - Adaptive Point Transformer [88.28498667506165]
Adaptive Point Cloud Transformer (AdaPT) is a standard PT model augmented by an adaptive token selection mechanism.
AdaPT dynamically reduces the number of tokens during inference, enabling efficient processing of large point clouds.
arXiv Detail & Related papers (2024-01-26T13:24:45Z) - Point Cloud Pre-training with Diffusion Models [62.12279263217138]
We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif)
PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
arXiv Detail & Related papers (2023-11-25T08:10:05Z) - Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
We propose a clustering based supervised learning scheme for point cloud analysis.
Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space.
Our algorithm shows notable improvements on famous point cloud segmentation datasets.
arXiv Detail & Related papers (2023-07-27T03:42:12Z) - GeoMAE: Masked Geometric Target Prediction for Self-supervised Point
Cloud Pre-Training [16.825524577372473]
We introduce a point cloud representation learning framework, based on geometric feature reconstruction.
We identify three self-supervised learning objectives to peculiar point clouds, namely centroid prediction, normal estimation, and curvature prediction.
Our pipeline is conceptually simple and it consists of two major steps: first, it randomly masks out groups of points, followed by a Transformer-based point cloud encoder.
arXiv Detail & Related papers (2023-05-15T17:14:55Z) - Dual Adaptive Transformations for Weakly Supervised Point Cloud
Segmentation [78.6612285236938]
We propose a novel DAT (textbfDual textbfAdaptive textbfTransformations) model for weakly supervised point cloud segmentation.
We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets.
arXiv Detail & Related papers (2022-07-19T05:43:14Z) - 3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models [17.487852393066458]
Existing verification method for point cloud model is time-expensive and computationally unattainable on large networks.
We propose 3DVerifier to tackle both challenges by adopting a linear relaxation function to bound the multiplication layer and combining forward and backward propagation.
Our approach achieves an orders-of-magnitude improvement in verification efficiency for the large network, and the obtained certified bounds are also significantly tighter than the state-of-the-art verifiers.
arXiv Detail & Related papers (2022-07-15T15:31:16Z) - 3DeformRS: Certifying Spatial Deformations on Point Clouds [61.62846778591536]
3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics.
Emerging concerns over the robustness of these models against real-world deformations must be addressed practically and reliably.
We propose 3DeformRS, a method to certify the robustness of point cloud Deep Neural Networks (DNNs) against real-world deformations.
arXiv Detail & Related papers (2022-04-12T10:24:31Z) - TPC: Transformation-Specific Smoothing for Point Cloud Models [9.289813586197882]
We propose a transformation-specific smoothing framework TPC, which provides robustness guarantees for point cloud models against semantic transformation attacks.
Experiments on several common 3D transformations show that TPC significantly outperforms the state of the art.
arXiv Detail & Related papers (2022-01-30T05:41:50Z) - Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point
Modeling [104.82953953453503]
We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud.
Experiments demonstrate that the proposed BERT-style pre-training strategy significantly improves the performance of standard point cloud Transformers.
arXiv Detail & Related papers (2021-11-29T18:59:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.