NP-Match: When Neural Processes meet Semi-Supervised Learning

TL;DR

NP-Match introduces a semi-supervised learning method that adapts neural processes for image classification, effectively leveraging unlabeled data and estimating uncertainty with less computational cost, outperforming existing methods.

Contribution

This work is the first to adapt neural processes for semi-supervised image classification, enhancing pseudo-label quality and uncertainty estimation with reduced computational overhead.

Findings

Outperforms state-of-the-art SSL methods on four datasets.

Effectively estimates uncertainty with less computation.

Improves pseudo-label quality through implicit data comparison.

Abstract

Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match. NP-Match is suited to this task for two reasons. Firstly, NP-Match implicitly compares data points when making predictions, and as a result, the prediction of each unlabeled data point is affected by the labeled data points that are similar to it, which improves the quality of pseudo-labels. Secondly, NP-Match is able to estimate uncertainty that can be used as a tool for selecting unlabeled samples with reliable pseudo-labels. Compared with uncertainty-based SSL methods implemented with Monte Carlo (MC) dropout, NP-Match estimates uncertainty with much less computational overhead, which can save time at both the training and the testing phases. We conducted extensive experiments on four public datasets, and NP-Match outperforms state-of-the-art (SOTA) results or achieves competitive results on them, which shows the effectiveness of NP-Match and its potential for SSL.