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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zhimin, Li, Bing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916479208783872
author Chen, Zhimin
Li, Bing
author_facet Chen, Zhimin
Li, Bing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08340
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning
Chen, Zhimin
Li, Bing
Computer Vision and Pattern Recognition
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.
title DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.08340