# SageMix: Saliency-Guided Mixup for Point Clouds

arXiv: https://arxiv.org/abs/2210.06944 · HTML: https://mlsanity.com/paper/2210.06944/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 58 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 30 of 33)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [Pointwise Convolutional Neural Networks](https://mlsanity.com/paper/1712.05245/) (2017)
- [PointCloud Saliency Maps](https://mlsanity.com/paper/1812.01687/) (2018)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [PointAugment: an Auto-Augmentation Framework for Point Cloud Classification](https://mlsanity.com/paper/2002.10876/) (2020)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [KeepAugment: A Simple Information-Preserving Data Augmentation Approach](https://mlsanity.com/paper/2011.11778/) (2020)
- [Octree guided CNN with Spherical Kernels for 3D Point Clouds](https://mlsanity.com/paper/1903.00343/) (2019)
- [A Graph-CNN for 3D Point Cloud Classification](https://mlsanity.com/paper/1812.01711/) (2018)

## Built on by (most cited first, 12 of 12)

- [Self-positioning Point-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2303.16450/) (2023)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding](https://mlsanity.com/paper/2312.11112/) (2023)
- [Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation](https://mlsanity.com/paper/2308.02982/) (2023)
- [PointPatchMix: Point Cloud Mixing with Patch Scoring](https://mlsanity.com/paper/2303.06678/) (2023)
- [MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency](https://mlsanity.com/paper/2303.09219/) (2023)
- [MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding](https://mlsanity.com/paper/2405.18523/) (2024)
- [InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory](https://mlsanity.com/paper/2505.19820/) (2025)
- [JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues](https://mlsanity.com/paper/2310.09503/) (2023)
- [Mixup Augmentation with Multiple Interpolations](https://mlsanity.com/paper/2406.01417/) (2024)
- [3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing](https://mlsanity.com/paper/2408.13788/) (2024)

## Abstract (arXiv)

Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity. Also, recent studies of saliency-aware Mixup in the image domain show that preserving discriminative parts is beneficial to improving the generalization performance. However, these Mixup-based data augmentations are underexplored in 3D vision, especially in point clouds. In this paper, we propose SageMix, a saliency-guided Mixup for point clouds to preserve salient local structures. Specifically, we extract salient regions from two point clouds and smoothly combine them into one continuous shape. With a simple sequential sampling by re-weighted saliency scores, SageMix preserves the local structure of salient regions. Extensive experiments demonstrate that the proposed method consistently outperforms existing Mixup methods in various benchmark point cloud datasets. With PointNet++, our method achieves an accuracy gain of 2.6% and 4.0% over standard training in 3D Warehouse dataset (MN40) and ScanObjectNN, respectively. In addition to generalization performance, SageMix improves robustness and uncertainty calibration. Moreover, when adopting our method to various tasks including part segmentation and standard 2D image classification, our method achieves competitive performance.