DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning

TL;DR

This paper introduces DyConfidMatch, a novel 3D semi-supervised learning method that employs dynamic thresholding and re-sampling to address data imbalance, improving classification and detection performance.

Contribution

It proposes a new approach using class-level confidence, dynamic thresholding, and re-sampling to effectively handle data imbalance in 3D semi-supervised learning.

Findings

Outperforms state-of-the-art methods in 3D classification and detection.

Effectively mitigates data imbalance issues.

Enhances utilization of unlabeled data from underrepresented classes.

Abstract

Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance, especially in 3D contexts. This study investigates class-level confidence as an indicator of learning status in 3D SSL, proposing a novel method that utilizes dynamic thresholding to better use unlabeled data, particularly from underrepresented classes. A re-sampling strategy is also introduced to mitigate bias towards well-represented classes, ensuring equitable class representation. Through extensive experiments in 3D SSL, our method surpasses state-of-the-art counterparts in classification and detection tasks, highlighting its effectiveness in tackling data imbalance. This approach presents a significant advancement in SSL for 3D datasets, providing a robust solution for data imbalance issues.