semi-supervised learning
PulseAugur coverage of semi-supervised learning — every cluster mentioning semi-supervised learning across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New VAST method improves semi-supervised learning by decoupling label generation
Researchers have developed VAST (Veracity-Aware Semi-Supervised Training), a novel approach to semi-supervised learning that decouples pseudo-label generation from classifier training. This method infers probabilistic b…
-
AI models identify biomarkers for liver cancer prediction · 2 sources tracked
Researchers have developed new methods using artificial intelligence to predict and identify biomarkers for hepatocellular carcinoma (HCC), a common form of liver cancer. One study constructed a dataset of 770 patient s…
-
Deep learning models show promise for label-efficient cancer diagnosis
This research paper explores three learning environments—supervised, semi-supervised, and self-supervised learning—for efficient cancer diagnosis using deep learning models. The study evaluated Residual Network-50, Visu…
-
New C-Score framework assesses SSL robustness against data contamination
Researchers have introduced C-Score, a novel framework designed to evaluate the robustness of semi-supervised learning (SSL) models, particularly when faced with unlabeled data contaminated by out-of-distribution (OOD) …
-
New frameworks tackle semi-supervised medical image segmentation challenges · 2 sources tracked
Two new research papers propose novel frameworks for semi-supervised medical image segmentation, addressing the challenges of limited annotated data and class imbalance. The first paper introduces Semantic Class Distrib…
-
LLM-as-a-Judge framework boosts AI reasoning with novel reward system
Researchers have developed a novel semi-supervised learning framework that utilizes a Large Language Model (LLM) as a judge to distill knowledge into AI models. This approach employs a continuous Chain-of-Thought (CoT) …
-
New PC-Seg framework uses sparse 2D annotations for accurate 3D OCT image segmentation
Researchers have developed PC-Seg, a novel framework for 3D segmentation of optical coherence tomography (OCT) images. This method utilizes semi-supervised learning to significantly reduce the need for extensive manual …
-
New MTSSL framework unifies pseudo-label thresholding in semi-supervised learning
Researchers have introduced Meta-Thresholding Semi-Supervised Learning (MTSSL), a novel framework that unifies the understanding of pseudo-label thresholding in semi-supervised learning. The study statistically explains…
-
New solver accelerates graph $p$-Laplacian semi-supervised learning
Researchers have developed a novel solver for graph $p$-Laplacian semi-supervised learning that achieves near-linear time complexity. This new method addresses limitations of existing solvers, particularly at higher val…
-
New framework enhances fetal ultrasound segmentation with semi-supervised learning
Researchers have developed DACL, a novel semi-supervised framework designed to improve the segmentation of fetal ultrasound images. This method utilizes both a lightweight convolutional network and a Transformer-based n…
-
New distillation method enhances AI for vehicle collision avoidance
Researchers have developed an instance-aware knowledge distillation framework to improve semi-supervised learning for collision avoidance systems. This method generates pseudo-labels by combining domain priors from a te…
-
New SADA method improves semi-supervised learning with black-box models
Researchers have developed SADA, a new method for safely and adaptively aggregating predictions from multiple black-box models in semi-supervised learning scenarios. This approach guarantees performance no worse than us…
-
New SCKAN Method Enhances Pancreas Segmentation with KANs
Researchers have developed SCKAN, a novel semi-supervised learning method for pancreas segmentation that utilizes Kolmogorov-Arnold Networks (KANs). This approach addresses limitations in existing methods caused by morp…
-
Medical AI research flags overconfidence in segmentation models
Researchers have identified a significant overconfidence issue in semi-supervised learning for 3D medical image segmentation. They argue that current methods often confuse prediction confidence with true uncertainty, le…