Unified Complementary Learning with Feature Perturbation for Semi-Supervised Learning
Open Access
- 7 January 2026
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 19 (1) , 56
Abstract
Semi-supervised learning has attracted widespread attention due to its ability to utilize both labeled and unlabeled data, leading to significant progress in recent years. Conventional semi-supervised learning approaches often rely on a strategy that combines weak and strong image-level augmentations and employs pseudo-labeling techniques, where high-confidence predictions are selected as pseudo-labels while low-confidence ones are discarded. However, such methods tend to overlook the useful information contained in low-confidence samples. Moreover, existing augmentation strategies are mostly limited to the image level and lack feature-level perturbations. To address these limitations, this paper proposes a semi-supervised learning method that integrates complementary labels and auxiliary feature perturbations, aiming to extract valuable information from low-confidence samples and expand the scope of feature-space perturbations. Experiments on the standard CIFAR-10 dataset show that under the extreme setting of only 4 labels per class, our method improves accuracy by 2.58% compared to Fixmatch. On the more complex STL-10 dataset, also with only 4 labels per class, the Top-1 accuracy is improved by 2.59%. In addition, systematic ablation studies are conducted to verify the effectiveness of each component.Keywords
Funding Information
- National Natural Science Foundation of China (U22A2047)
- National Natural Science Foundation of China (62371173)
This publication has 38 references indexed in Scilit:
- A comprehensive survey on contrastive learningNeurocomputing, 2024
- 3D medical image segmentation based on semi-supervised learning using deep co-trainingApplied Soft Computing, 2024
- Boosting semi-supervised learning with Contrastive Complementary LabelingNeural Networks, 2023
- Improved Object Detection Method Utilizing YOLOv7-Tiny for Unmanned Aerial Vehicle Photographic ImageryAlgorithms, 2023
- MutexMatch: Semi-Supervised Learning With Mutex-Based Consistency RegularizationIEEE Transactions on Neural Networks and Learning Systems, 2022
- A Survey on Deep Semi-Supervised LearningIEEE Transactions on Knowledge and Data Engineering, 2022
- Semi-Supervised Contrastive Learning With Similarity Co-CalibrationIEEE Transactions on Multimedia, 2022
- Contrastive Representation Learning: A Framework and ReviewIEEE Access, 2020
- A survey on semi-supervised learningMachine Learning, 2019
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015