# Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Data

arXiv: https://arxiv.org/abs/2409.13977 · HTML: https://mlsanity.com/paper/2409.13977/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 21 Sep 2024.

## Builds on (most cited first, 22 of 22)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [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)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning](https://mlsanity.com/paper/2301.10921/) (2023)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data](https://mlsanity.com/paper/2303.11066/) (2023)
- [ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization](https://mlsanity.com/paper/2208.08631/) (2022)
- [Multimodal Semi-Supervised Learning for 3D Objects](https://mlsanity.com/paper/2110.11601/) (2021)
- [Class-Level Confidence Based 3D Semi-Supervised Learning](https://mlsanity.com/paper/2210.10138/) (2022)
- [SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learning](https://mlsanity.com/paper/2310.15787/) (2023)
- [Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis](https://mlsanity.com/paper/2108.02104/) (2021)
- [Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning](https://mlsanity.com/paper/2309.03598/) (2023)
- [Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data](https://mlsanity.com/paper/2306.01222/) (2023)

## Built on by (most cited first, 2 of 2)

- [An Adapter-free Fine-tuning Approach for Tuning 3D Foundation Models](https://mlsanity.com/paper/2603.23730/) (2026)
- [Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning](https://mlsanity.com/paper/2606.18472/) (2026)

## Abstract (arXiv)

Semi-supervised learning (SSL) has shown its effectiveness in learning effective 3D representation from a small amount of labelled data while utilizing large unlabelled data. Traditional semi-supervised approaches rely on the fundamental concept of predicting pseudo-labels for unlabelled data and incorporating them into the learning process. However, we identify that the existing methods do not fully utilize all the unlabelled samples and consequently limit their potential performance. To address this issue, we propose AllMatch, a novel SSL-based 3D classification framework that effectively utilizes all the unlabelled samples. AllMatch comprises three modules: (1) an adaptive hard augmentation module that applies relatively hard augmentations to the high-confident unlabelled samples with lower loss values, thereby enhancing the contribution of such samples, (2) an inverse learning module that further improves the utilization of unlabelled data by learning what not to learn, and (3) a contrastive learning module that ensures learning from all the samples in both supervised and unsupervised settings. Comprehensive experiments on two popular 3D datasets demonstrate a performance improvement of up to 11.2% with 1% labelled data, surpassing the SOTA by a significant margin. Furthermore, AllMatch exhibits its efficiency in effectively leveraging all the unlabelled data, demonstrated by the fact that only 10% of labelled data reaches nearly the same performance as fully-supervised learning with all labelled data. The code of our work is available at: https://github.com/snehaputul/AllMatch.