# Class-Level Confidence Based 3D Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2210.10138 · HTML: https://mlsanity.com/paper/2210.10138/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 30 of 37)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](https://mlsanity.com/paper/2006.07529/) (2020)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images](https://mlsanity.com/paper/1511.02300/) (2015)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2012.04355/) (2020)

## Built on by (most cited first, 14 of 14)

- [Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models](https://mlsanity.com/paper/2305.08776/) (2023)
- [MemoryMamba: Memory-Augmented State Space Model for Defect Recognition](https://mlsanity.com/paper/2405.03673/) (2024)
- [CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction](https://mlsanity.com/paper/2304.14633/) (2023)
- [Cross-Task Multi-Branch Vision Transformer for Facial Expression and Mask Wearing Classification](https://mlsanity.com/paper/2404.14606/) (2024)
- [Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes](https://mlsanity.com/paper/2404.06050/) (2024)
- [Adaptive speed planning for Unmanned Vehicle Based on Deep Reinforcement Learning](https://mlsanity.com/paper/2404.17379/) (2024)
- [TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation](https://mlsanity.com/paper/2405.16847/) (2024)
- [Exploiting Diffusion Prior for Out-of-Distribution Detection](https://mlsanity.com/paper/2406.11105/) (2024)
- [SAM-Guided Masked Token Prediction for 3D Scene Understanding](https://mlsanity.com/paper/2410.12158/) (2024)
- [Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Data](https://mlsanity.com/paper/2409.13977/) (2024)
- [Unsupervised Gait Recognition with Selective Fusion](https://mlsanity.com/paper/2303.10772/) (2023)
- [DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning](https://mlsanity.com/paper/2411.08340/) (2024)
- [An Adapter-free Fine-tuning Approach for Tuning 3D Foundation Models](https://mlsanity.com/paper/2603.23730/) (2026)
- [TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2409.10901/) (2024)

## Abstract (arXiv)

Recent state-of-the-art method FlexMatch firstly demonstrated that correctly estimating learning status is crucial for semi-supervised learning (SSL). However, the estimation method proposed by FlexMatch does not take into account imbalanced data, which is the common case for 3D semi-supervised learning. To address this problem, we practically demonstrate that unlabeled data class-level confidence can represent the learning status in the 3D imbalanced dataset. Based on this finding, we present a novel class-level confidence based 3D SSL method. Firstly, a dynamic thresholding strategy is proposed to utilize more unlabeled data, especially for low learning status classes. Then, a re-sampling strategy is designed to avoid biasing toward high learning status classes, which dynamically changes the sampling probability of each class. To show the effectiveness of our method in 3D SSL tasks, we conduct extensive experiments on 3D SSL classification and detection tasks. Our method significantly outperforms state-of-the-art counterparts for both 3D SSL classification and detection tasks in all datasets.