PointCutMix: Regularization strategy for point cloud classification

Zhang, Jinlai; Chen, Lyujie; Ouyang, Bo; Liu, Binbin; Zhu, Jihong; Chen, Yujing; Meng, Yanmei; Wu, Dalei

doi:10.1016/j.neucom.2022.07.049

Cited by 58 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our work, we develop a simple and automatic part substitution scheme for generating shapes with proper structural and geometric variations from a small number of labeled 3D shapes, whose quality is sufficient to improve network training. We also notice that recent point cloud augmentation techniques [64][65][66] that mix points of different shapes randomly to generate more varied shapes can enhance point cloud classification, and can be extended to shape segmentation [67]. However, random augmentation does not respect shape structure and can lead to limited improvements only, as our experiments show.…”

Section: Structure-aware Shape Synthesismentioning

confidence: 72%

“…Concurrent work to this work, PointCutMix [67] proposes a data augmentation method which finds the optimal assignment between two labeled point clouds and generates new training data by replacing points in one sample with their optimally assigned pairs. We implemented their approach and used the generated shapes to enhance training.…”

Section: Multilevel Consistency Loss and Part Substitutionmentioning

confidence: 99%

“…12, we render the augmented shapes generated by the approach of Ref. [67]. We can observe many implausible shape parts which do not assist training.…”

Section: Data Augmentation By Part Substitutionmentioning

confidence: 99%

See 2 more Smart Citations

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

et al. 2023

View full text Add to dashboard Cite

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data. For the unlabeled data, we present a novel multilevel consistency loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point level, part level, and hierarchical level. For the labeled data, we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance training. Our method has been extensively validated on the task of 3D object semantic segmentation on PartNet and ShapeNetPart, and indoor scene semantic segmentation on ScanNet. It exhibits superior performance to existing semi-supervised and unsupervised pre-training 3D approaches.

show abstract

Section: Structure-aware Shape Synthesismentioning

confidence: 72%

Section: Multilevel Consistency Loss and Part Substitutionmentioning

confidence: 99%

See 1 more Smart Citation

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Augmentation. Most 3D data augmentation techniques are object-centric [10,36,54,78] and thus not generalizable to scenes. Panoptic-PolarNet [83] over-samples rare instance points during training.…”

Section: Related Workmentioning

confidence: 99%

Rethinking Range View Representation for LiDAR Segmentation

Kong¹,

Liu²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point-or voxel-based methods as they often yield better performance than the traditional range view representation. In this work, we unveil several key factors in building powerful range view models. We observe that the "many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer -a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing -that better handles the learning and processing of LiDAR point clouds from the range view. We further introduce a Scalable Training from Range view (STR) strategy that trains on arbitrary lowresolution 2D range images, while still maintaining satisfactory 3D segmentation accuracy. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i.e., SemanticKITTI, nuScenes, and ScribbleKITTI. 𝜙 𝜃 Cylindrical Coordinate Cartesian Coordinate 𝑧 𝑥 𝑦 Many-to-One Adjacent points are mapped to the same grid Empty Grid Void cells in the range image due to 3D sparsity Deformation Shapes are distorted due to limited FOVs road car

show abstract

“…6. Moreover, we study data augmentation strategies [14,69,72] as potential solutions to improve corruption robustness, but find that they provide a little robustness gain, leaving robustness enhancement of 3D object detection an open problem for future research.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving

Dong¹,

Kang²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

3D object detection is an important task in autonomous driving to perceive the surroundings. Despite the excellent performance, the existing 3D detectors lack the robustness to real-world corruptions caused by adverse weathers, sensor noises, etc., provoking concerns about the safety and reliability of autonomous driving systems. To comprehensively and rigorously benchmark the corruption robustness of 3D detectors, in this paper we design 27 types of common corruptions for both LiDAR and camera inputs considering real-world driving scenarios. By synthesizing these corruptions on public datasets, we establish three corruption robustness benchmarks-KITTI-C, nuScenes-C, and Waymo-C. Then, we conduct large-scale experiments on 24 diverse 3D object detection models to evaluate their corruption robustness. Based on the evaluation results, we draw several important findings, including: 1) motion-level corruptions are the most threatening ones that lead to significant performance drop of all models; 2) LiDAR-camera fusion models demonstrate better robustness; 3) camera-only models are extremely vulnerable to image corruptions, showing the indispensability of LiDAR point clouds. We release the benchmarks and codes at https://github.com/kkkcx/ 3D_Corruptions_AD. We hope that our benchmarks and findings can provide insights for future research on developing robust 3D object detection models.

show abstract

PointCutMix: Regularization strategy for point cloud classification

Cited by 58 publications

References 27 publications

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

Rethinking Range View Representation for LiDAR Segmentation

Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving

Contact Info

Product

Resources

About