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

TL;DR

This paper introduces AllMatch, a novel semi-supervised learning framework for 3D classification that fully utilizes unlabelled data through adaptive augmentation, inverse learning, and contrastive learning, achieving state-of-the-art results.

Contribution

AllMatch is the first framework to effectively leverage all unlabelled samples in 3D SSL by combining adaptive augmentation, inverse learning, and contrastive learning modules.

Findings

Up to 11.2% performance improvement with 1% labelled data.

Nearly full performance with only 10% labelled data compared to fully-supervised learning.

Outperforms state-of-the-art methods on two 3D datasets.

Abstract

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.