# Confidence-Guided Data Augmentation for Improved Semi-Supervised Training

Source: [Confidence-Guided Data Augmentation for Improved Semi-Supervised Training](<https://www.sota2.com/research/paper/68fa6e9b1e209131cea410b3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:01:51.507Z

Authors: Fadoua Khmaissia, Hichem Frigui

Published: 2022-09-16T21:23:19.000Z

## Abstract

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and correctly classified samples with low confidence values. These samples are then used to train a Variational AutoEncoder (VAE). Next, the VAE is used to generate synthetic images. Finally, the generated synthetic images are used in conjunction with the original labeled images to train a new model in a semi-supervised fashion. Empirical results on benchmark datasets such as STL10 and CIFAR-100 show that the synthetically generated samples can further diversify the training data, leading to improvement in image classification in comparison with the fully supervised baseline approaches using only the available data.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.08174>)

[PDF](<https://arxiv.org/pdf/2209.08174.pdf>)