Log In Sign Up

AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning

by   Jiwon Kim, et al.

Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. Conventional methods focused on extracting a pseudo label from individual unlabeled data sample and thus they mostly struggled to handle inaccurate or noisy pseudo labels, which degenerate performance. In this paper, we address this limitation with a novel SSL framework for aggregating pseudo labels, called AggMatch, which refines initial pseudo labels by using different confident instances. Specifically, we introduce an aggregation module for consistency regularization framework that aggregates the initial pseudo labels based on the similarity between the instances. To enlarge the aggregation candidates beyond the mini-batch, we present a class-balanced confidence-aware queue built with the momentum model, encouraging to provide more stable and consistent aggregation. We also propose a novel uncertainty-based confidence measure for the pseudo label by considering the consensus among multiple hypotheses with different subsets of the queue. We conduct experiments to demonstrate the effectiveness of AggMatch over the latest methods on standard benchmarks and provide extensive analyses.


page 1

page 10

page 11


Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

While semi-supervised learning (SSL) has proven to be a promising way fo...

Field Extraction from Forms with Unlabeled Data

We propose a novel framework to conduct field extraction from forms with...

Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition

This paper looks at semi-supervised learning (SSL) for image-based text ...

Semi-supervised learning by selective training with pseudo labels via confidence estimation

We propose a novel semi-supervised learning (SSL) method that adopts sel...

Debiased Learning from Naturally Imbalanced Pseudo-Labels for Zero-Shot and Semi-Supervised Learning

This work studies the bias issue of pseudo-labeling, a natural phenomeno...

Density-Aware Graph for Deep Semi-Supervised Visual Recognition

Semi-supervised learning (SSL) has been extensively studied to improve t...

Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondence

Establishing dense correspondences across semantically similar images is...