Results 11 to 20 of about 10,284,296 (292)
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible classes may not be initially available for training, and may be given incrementally. Deep learning models need to deal with this two-fold problem in order to perform well in real-life situations.
Pratik Mazumder +2 more
openaire +5 more sources
Tuberculosis detection using few shot learning [PDF]
Scientific ReportsTuberculosis (TB), a contagious disease, significantly affects lungs functioning. Amongst multiple detection methodologies, Chest X-ray analysis is considered the most effective methodology. Traditional Deep Learning methodologies have shown good results
Kamran Riasat +5 more
doaj +2 more sources
Federated knee injury diagnosis using few shot learning [PDF]
Frontiers in Artificial IntelligenceIntroductionKnee injuries, especially Anterior Cruciate Ligament (ACL) tears and meniscus tears, are becoming increasingly common and can severely restrict mobility and quality of life.
Chirag Goel, Anita X, Jani Anbarasi L
doaj +2 more sources
MetaChest: generalized few-shot learning of pathologies from chest X-rays [PDF]
Visual Computing for Industry, Biomedicine, and ArtThe limited availability of annotated data presents a major challenge in applying deep learning methods to medical image analysis. Few-shot learning methods aim to recognize new classes from only a few labeled examples.
Berenice Montalvo-Lezama +1 more
doaj +2 more sources
Learning multi-level weight-centric features for few-shot learning [PDF]
, 2022 Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the problem ...
Liang, Mingjiang +4 more
core +2 more sources
, 2018 Fine-grained image classification with a few-shot classifier is a highly challenging open problem at the core of a numerous data labeling applications.
Adamu Ali-Gombe (19726213) +3 more
core +5 more sources
Few-Shot Few-Shot Learning and the role of Spatial Attention [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data, ignoring the amount of prior knowledge that a human may have accumulated before learning new tasks.
Lifchitz, Yann +2 more
openaire +3 more sources
Survey on Machine Learning Methods for Small Sample Data [PDF]
Jisuanji gongcheng, 2022 Few-shot learning is a type of machine learning method for small sample data that operates by using less supervised sample data to build machine learning models that can solve practical problems.Therefore, few-shot learning can be used to solve the ...
CHEN Liangchen, FU Deyin
doaj +1 more source
Multi-Similarity Enhancement Network for Few-Shot Segmentation
IEEE Access, 2023 Few-Shot Segmentation (FSS) is challenging for intra-class diversity and support sample scarcity. Many works focus on the class-wise or pixel-wise similarity between the support foreground and query sample while neglecting the support background, which ...
Hao Chen, Zhe-Ming Lu, Yang-Ming Zheng
doaj +1 more source
Filtering Specialized Change in a Few-Shot Setting
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 The aim of change detection in remote sensing usually is not to find all differences between the observations, but rather only specific types of change, such as urban development, deforestation, or even more specialized categories like roadwork. However,
Martin Hermann +2 more
doaj +1 more source