Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data. [PDF]
Cancers (Basel), 2021 Deep learning requires a large amount of data to perform well. However, the field of medical image analysis suffers from a lack of sufficient data for training deep learning models.
Alzubaidi L +8 more
europepmc +2 more sources
RenderGAN: Generating Realistic Labeled Data [PDF]
Frontiers in Robotics and AI, 2018 Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting.
Leon Sixt, Benjamin Wild, Tim Landgraf
doaj +2 more sources
JMIR Med Inform, 2022 Background Automated extraction of symptoms from clinical notes is a challenging task owing to the multidimensional nature of symptom description. The availability of labeled training data is extremely limited owing to the nature of the data containing ...
Humbert-Droz M, Mukherjee P, Gevaert O.
europepmc +2 more sources
Weakly Labeled Data Augmentation for Deep Learning: A Study on COVID-19 Detection in Chest X-Rays. [PDF]
Diagnostics (Basel), 2020 The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic resulting in over 2.7 million infected individuals and over 190,000 deaths and growing.
Rajaraman S, Antani S.
europepmc +2 more sources
MISM: A Medical Image Segmentation Metric for Evaluation of Weak Labeled Data [PDF]
Diagnostics, 2023 Performance measures are an important tool for assessing and comparing different medical image segmentation algorithms. Unfortunately, the current measures have their weaknesses when it comes to assessing certain edge cases.
Dennis Hartmann +6 more
doaj +2 more sources
Editorial: Deep learning with limited labeled data for vision, audio, and text [PDF]
Frontiers in Artificial Intelligence, 2023 Marko Orescanin +4 more
doaj +2 more sources
Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 Chain-of-thought (CoT) advances the reasoning abilities of large language models (LLMs) and achieves superior performance in complex reasoning tasks.
Kashun Shum, Shizhe Diao, Tong Zhang
semanticscholar +1 more source
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort [PDF]
Computer Vision and Pattern Recognition, 2021 We introduce DatasetGAN: an automatic procedure to generate massive datasets of high-quality semantically segmented images requiring minimal human effort.
Yuxuan Zhang +7 more
semanticscholar +1 more source
Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity [PDF]
International Conference on Smart Computing, 2023 The use of supervised learning for Human Activity Recognition (HAR) on mobile devices leads to strong classification performances. Such an approach, however, requires large amounts of labeled data, both for the initial training of the models and for ...
Riccardo Presotto +5 more
semanticscholar +1 more source
Robust Medical Image Classification From Noisy Labeled Data With Global and Local Representation Guided Co-Training [PDF]
IEEE Transactions on Medical Imaging, 2022 Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data.
Cheng Xue +4 more
semanticscholar +1 more source