LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching

TL;DR

LiDAM is a semi-supervised learning method that combines localized domain adaptation and iterative matching to improve classification accuracy with limited labeled data, achieving state-of-the-art results on CIFAR-100.

Contribution

The paper introduces LiDAM, a novel semi-supervised approach that integrates localized domain shifts and an iterative matching process for better pseudo-labeling.

Findings

LiDAM outperforms FixMatch on CIFAR-100 with 2500 labels (73.50% vs. 71.82%).

Localized domain adaptation improves feature invariance and clustering.

Iterative matching enhances pseudo-label accuracy and model training.

Abstract

Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a semi-supervised learning approach rooted in both domain adaptation and self-paced learning. LiDAM first performs localized domain shifts to extract better domain-invariant features for the model that results in more accurate clusters and pseudo-labels. These pseudo-labels are then aligned with real class labels in a self-paced fashion using a novel iterative matching technique that is based on majority consistency over high-confidence predictions. Simultaneously, a final classifier is trained to predict ground-truth labels until convergence. LiDAM achieves state-of-the-art performance on the CIFAR-100 dataset, outperforming FixMatch (73.50% vs. 71.82%) when using 2500 labels.