Jul 2026· IEEE Transactions on Image Processing· Vol 35, pp. 8386-8400· 0 citations· 61 references
MedicineComputer Science
Abstract
Existing semi-supervised learning (SSL) methods rely predominantly on pseudo-labeling and consistency regularization to leverage unlabeled data, demonstrating significant performance improvements. However, we pinpoint that these methods suffer from a confidence-for-weighting issue, overvaluing high-confidence pseudo-labels while undervaluing low-confidence yet informative samples that are critical for robust generalization. In this paper, we introduce EntropyMatch, an entropy-driven SSL framework that redefines sample importance through prediction entropy rather than confidence alone. EntropyMatch employs a bidirectional weighting strategy: upward exploitation exploits reliable hard samples to refine decision boundaries while downward exploration cautiously explores uncertain ones to reduce noise. Additionally, EntropyMatch features an adaptive training mechanism that aligns with model maturity, shifting focus from safe exploration to strategic exploitation as training progresses. Experiments on eight benchmarks across various SSL tasks—spanning image classification, facial expression recognition, and human action recognition—validate EntropyMatch’s robustness and effectiveness. It consistently achieves state-of-the-art results, notably matching state-of-the-art LION’s performance on RAF-DB with just half the labeled data, demonstrating superior data efficiency and generalization.
Semi-supervised learning (SSL) is an effective approach to leverage limited labeled data alongside abundant unlabeled data. While methods like MarginMatch have shown promise by using the average pseudo margin (APM) to evaluate pseudo-label reliability, they face two limitations: (1) APM struggles to distinguish correctly and incorrectly pseudo-labeled classes for hard-to-learn samples, and (2) fixed-percentile thresholding leads to suboptimal pseudo-label utilization throughout training. To address these challenges, we propose APIMatch, a novel SSL framework introducing the average pseudo integrated margin (APIM) metric and a negative-sample-aware dynamic percentile thresholding strategy. The core novelty lies in jointly modeling the pseudo-labeled class and competitive non-pseudo-labeled classes to accurately re-evaluate hard-to-learn samples, coupled with a confidence-distribution-aware adaptive threshold. Specifically, APIM jointly considers the logit differences between the pseudo-labeled class and both the largest and second-largest non-pseudo-labeled classes, enabling more accurate confidence evaluation for hard-to-learn samples. In addition, our dynamic thresholding strategy constructs a pseudo-negative-sample reference set to model confidence distributions and adaptively adjusts the percentile threshold based on training progression, improving both recall in early stages and precision in later stages. Extensive experiments on CIFAR-10, CIFAR-100, and STL-10 demonstrate that APIMatch achieves competitive performance against state-of-the-art methods, particularly in extremely low-label scenarios. Under the 1 label per class setting, APIMatch achieves error rates of
1.84
%
and
36.7
%
on CIFAR-10 and CIFAR-100, respectively. On STL-10 with only 4 labels per class, APIMatch achieves an error rate of
18.47
%
±
0.65
%
, representing a
6.9
%
absolute accuracy improvement over MarginMatch, demonstrating strong robustness under severe label scarcity.
Xianmin Wang, Dong-Yuan Tian, Jing Li· The European Journal on Arti...· 0 citations
Tri-training is a classic semi-supervised learning framework that improves classifier performance by exploiting unlabeled data. However, it suffers from invalid view redundancy assumption and severe pseudo-label noise in real-world applications, which leads to performance degradation. To address these problems, this paper proposes an improved Tri-training semi-supervised classification algorithm based on adaptive neighborhood entropy, denoted as ANET. The algorithm retains the basic Tri-training structure and introduces a lightweight noise suppression module. Specifically, it constructs local neighborhoods for pseudo-labeled samples through k-nearest neighbor search, quantifies sample reliability by calculating neighborhood distribution entropy, and removes low-confidence noise samples with an adaptive threshold. Experiments are conducted on nine UCI datasets with four evaluation metrics: accuracy, precision, recall, and F1-measure. Compared with the standard Tri-training and five state-of-the-art improved algorithms, ANET achieves higher accuracy on 8 datasets, and the average accuracy is increased by 4.2%–8.7%. The results show that the algorithm effectively suppresses pseudo-label noise and has stronger robustness and practicality in real classification tasks.
Xiangxiang Cai, Song Li, Yulin Zhang· International Conference on...· 0 citations
This work introduces a novel framework, Gaussian Bridge Consistency (GBC), to address challenges of semi-supervised learning by constructing semantic interpolation paths between unlabeled samples and high-quality class anchors, and proposes BridgeMix, a confidence-aware feature mixing strategy that interpolates both sample and anchor pairs to amplify cross-sample generalization.
Hong-Yang He, Xin-Yuan Song, Yan Zhong et al.· 0 citations
C-Score, a compact framework that evaluates training behavior in three complementary spaces: prediction, feature representation, and optimization, suggests that clean accuracy alone is insufficient for evaluating SSL robustness in open-world environments, and that internal diagnostic signals are necessary for more reliable robustness assessment under unlabeled contamination.
Tsao-Lun Chen, Chicheng Fu, Han-Yi Chou et al.· 0 citations
