PointAugment: An Auto-Augmentation Framework for Point Cloud Classification

@article{Li2020PointAugmentAA,
  title={PointAugment: An Auto-Augmentation Framework for Point Cloud Classification},
  author={Ruihui Li and Xianzhi Li and Pheng-Ann Heng and Chi-Wing Fu},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={6377-6386}
}
  • Ruihui Li, Xianzhi Li, Chi-Wing Fu
  • Published 25 February 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods for 2D images, PointAugment is sample-aware and takes an adversarial learning strategy to jointly optimize an augmentor network and a classifier network, such that the augmentor can learn to produce augmented samples that best fit the classifier. Moreover, we… 
On Automatic Data Augmentation for 3D Point Cloud Classification
TLDR
This work proposes to automatically learn a data augmentation strategy using bilevel optimization, which achieves competitive performance on both tasks and provides further insight into the augmentor’s ability to learn the validation set distribution.
PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification
TLDR
PatchAugment is presented, a data augmentation framework to apply different augmentation techniques to the local neighborhoods to alleviate limitations such as overfitting, reduced robustness, and lower generalization in deep neural network models.
Point Cloud Augmentation with Weighted Local Transformations
TLDR
A simple and effective augmentation method called PointWOLF for point cloud augmentation, which produces smoothly varying non-rigid deformations by locally weighted transformations centered at multiple anchor points that allow diverse and realistic augmentations.
PointDrop: Improving Object Detection from Sparse Point Clouds via Adversarial Data Augmentation
TLDR
PointDrop is proposed, which learns to drop the features of some key points in the point clouds to generate challenging sparse samples for data augmentation and is able to adjust the difficulty of the generated samples based on the capacity of the detector and thus progressively improve the performance of the detectors.
Pattern-Aware Data Augmentation for LiDAR 3D Object Detection
TLDR
This paper proposes pattern-aware ground truth sampling, a data augmentation technique that downsamples an object's point cloud based on the LiDAR's characteristics so that the network has more diverse training examples and can generalize to detecting farther objects more effectively.
Point Cloud Upsampling via Disentangled Refinement
TLDR
This work proposes to disentangle the task based on its multi-objective nature and formulate two cascaded sub-networks, a dense generator and a spatial refiner, and designs a pair of local and global refinement units in the spatial refiners to evolve a coarse feature map.
Direct Differentiable Augmentation Search
TLDR
This paper proposes an efficient differentiable search algorithm called Direct Differentiable Augmentation Search (DDAS), which exploits meta-learning with one-step gradient update and continuous relaxation to the expected training loss for efficient search.
LiDAR-Aug: A General Rendering-based Augmentation Framework for 3D Object Detection
TLDR
The proposed LiDAR-Aug is a plug-and-play module that can be easily integrated into different types of 3D object detection frameworks and is more realistic and effective than the traditional object augmentation methods.
PointMixup: Augmentation for Point Clouds
TLDR
It is proved that the PointMixup finds the shortest path between two point clouds and that the interpolation is assignment invariant and linear, which allows to introduce strong interpolation-based regularizers such as mixup and manifold mixup to the point cloud domain.
...
1
2
3
4
...

References

SHOWING 1-10 OF 53 REFERENCES
PU-Net: Point Cloud Upsampling Network
TLDR
A data-driven point cloud upsampling technique to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space, which shows that its upsampled points have better uniformity and are located closer to the underlying surfaces.
PU-GAN: A Point Cloud Upsampling Adversarial Network
TLDR
A new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces.
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Deep Learning on Point Sets for 3 D Classification and Segmentation
  • C. Qi
  • Computer Science
  • 2016
TLDR
This paper designs a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input, and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
TLDR
RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis, achieves the state of the arts and a hierarchical architecture can be developed to achieve contextual shape-aware learning for Point cloud analysis.
Adversarial AutoAugment
TLDR
An adversarial method to arrive at a computationally-affordable solution called Adversarial AutoAugment, which can simultaneously optimize target related object and augmentation policy search loss and demonstrate significant performance improvements over state-of-the-art.
Learning to Compose Domain-Specific Transformations for Data Augmentation
TLDR
The proposed method can make use of arbitrary, non-deterministic transformation functions, is robust to misspecified user input, and is trained on unlabeled data, which can be used to perform data augmentation for any end discriminative model.
Fast AutoAugment
TLDR
This paper proposes an algorithm called Fast AutoAugment that finds effective augmentation policies via a more efficient search strategy based on density matching that speeds up the search time by orders of magnitude while achieves comparable performances on image recognition tasks with various models and datasets.
LassoNet: Deep Lasso-Selection of 3D Point Clouds
TLDR
This work introduces LassoNet, a new deep neural network for lasso selection of 3D point clouds, attempting to learn a latent mapping from viewpoint and lasso to point cloud regions, and improves the method scalability via an intention filtering and farthest point sampling.
Efficient Learning on Point Clouds With Basis Point Sets
TLDR
This work proposes basis point sets as a highly efficient and fully general way to process point clouds with machine learning algorithms and achieves performance comparable to the state-of-the-art computationally intense multi-step frameworks in one network pass that can be done in less than 1ms.
...
1
2
3
4
5
...