Results 291 to 300 of about 25,867,085 (318)
Some of the next articles are maybe not open access.
Shoestring: Graph-Based Semi-Supervised Classification With Severely Limited Labeled Data
Computer Vision and Pattern Recognition, 2020Graph-based semi-supervised learning has been shown to be one of the most effective classification approaches, as it can exploit connectivity patterns between labeled and unlabeled samples to improve learning performance.
Wanyu Lin, Zhaolin Gao, Baochun Li
semanticscholar +1 more source
Learning to Count in the Crowd from Limited Labeled Data
European Conference on Computer Vision, 2020Recent crowd counting approaches have achieved excellent performance. However, they are essentially based on fully supervised paradigm and require large number of annotated samples. Obtaining annotations is an expensive and labour-intensive process.
Vishwanath A. Sindagi +4 more
semanticscholar +1 more source
Learning From Weakly Labeled Data Based on Manifold Regularized Sparse Model
IEEE Transactions on Cybernetics, 2020In multilabel learning, each training example is represented by a single instance, which is relevant to multiple class labels simultaneously. Generally, all relevant labels are considered to be available for labeled data.
Jia Zhang, Shaozi Li, Min Jiang, K. Tan
semanticscholar +1 more source
International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019
In the medical domain, the lack of large training data sets and benchmarks is often a limiting factor for training deep neural networks. In contrast to expensive manual labeling, computer simulations can generate large and fully labeled data sets with a ...
Micha Pfeiffer +14 more
semanticscholar +1 more source
In the medical domain, the lack of large training data sets and benchmarks is often a limiting factor for training deep neural networks. In contrast to expensive manual labeling, computer simulations can generate large and fully labeled data sets with a ...
Micha Pfeiffer +14 more
semanticscholar +1 more source
Robust Graph-Based Semisupervised Learning for Noisy Labeled Data via Maximum Correntropy Criterion
IEEE Transactions on Cybernetics, 2019Semisupervised learning (SSL) methods have been proved to be effective at solving the labeled samples shortage problem by using a large number of unlabeled samples together with a small number of labeled samples. However, many traditional SSL methods may
Bo Du +4 more
semanticscholar +1 more source
Applied intelligence (Boston), 2022
Puneet Kumar, Kshitij Pathania, B. Raman
semanticscholar +1 more source
Puneet Kumar, Kshitij Pathania, B. Raman
semanticscholar +1 more source
Semi-supervised geological disasters named entity recognition using few labeled data
GeoInformatica, 2022Xinya Lei +4 more
semanticscholar +1 more source
An overview of real‐world data sources for oncology and considerations for research
Ca-A Cancer Journal for Clinicians, 2022Lynne Penberthy +2 more
exaly