Revisiting weak-to-strong consistency in semi-supervised semantic segmentation

L Yang, L Qi, L Feng, W Zhang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch
from semi-supervised classification, where the prediction of a weakly perturbed image …

Boosting semi-supervised learning by exploiting all unlabeled data

Y Chen, X Tan, B Zhao, Z Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of
mitigating the dependence on large labeled datasets. The latest methods (eg, FixMatch) use …

Revisiting consistency regularization for semi-supervised learning

Y Fan, A Kukleva, D Dai, B Schiele - International Journal of Computer …, 2023 - Springer
Consistency regularization is one of the most widely-used techniques for semi-supervised
learning (SSL). Generally, the aim is to train a model that is invariant to various data …

Dc-ssl: Addressing mismatched class distribution in semi-supervised learning

Z Zhao, L Zhou, Y Duan, L Wang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Consistency-based Semi-supervised learning (SSL) has achieved promising performance
recently. However, the success largely depends on the assumption that the labeled and …

Pefat: Boosting semi-supervised medical image classification via pseudo-loss estimation and feature adversarial training

Q Zeng, Y **e, Z Lu, Y **a - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
Pseudo-labeling approaches have been proven beneficial for semi-supervised learning
(SSL) schemes in computer vision and medical imaging. Most works are dedicated to finding …

Semi-supervised object detection via multi-instance alignment with global class prototypes

A Li, P Yuan, Z Li - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Semi-Supervised object detection (SSOD) aims to improve the generalization ability of
object detectors with large-scale unlabeled images. Current pseudo-labeling-based SSOD …

Laplacenet: A hybrid graph-energy neural network for deep semisupervised classification

P Sellars, AI Aviles-Rivero… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Semisupervised learning (SSL) has received a lot of recent attention as it alleviates the need
for large amounts of labeled data which can often be expensive, requires expert knowledge …

Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations

LG Jiménez, L Dierckx, M Amodei… - Proceedings of the …, 2023 - openaccess.thecvf.com
Real-world segmentation tasks in digital pathology require a great effort from human experts
to accurately annotate a sufficiently high number of images. Hence, there is a huge interest …

Fishermatch: Semi-supervised rotation regression via entropy-based filtering

Y Yin, Y Cai, H Wang, B Chen - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Estimating the 3DoF rotation from a single RGB image is an important yet challenging
problem. Recent works achieve good performance relying on a large amount of expensive …

Towards semi-supervised learning with non-random missing labels

Y Duan, Z Zhao, L Qi, L Zhou… - Proceedings of the …, 2023 - openaccess.thecvf.com
Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective
usage of unlabeled data. While existing SSL methods focus on the traditional setting, a …