Results 31 to 40 of about 29,104 (263)

Few-shot Learning: Methods and Applications [PDF]

ITM Web of Conferences
The Few-shot learning (FSL) approach distills meaningful features from a constrained sample set, allowing models to swiftly adjust to novel tasks and decreasing the dependency on extensive datasets. This approach leverages methods involving meta-learning,
Li Jiaxiang, Li Mingyang
doaj   +1 more source

Active Few-Shot Learning with FASL

, 2022
Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly develop and deploy new models for real world problems and business needs.
Thomas Müller 0009, Guillermo Pérez-Torró, Angelo Basile, Marc Franco-Salvador   +3 more
openaire   +2 more sources

Learning few-shot imitation as cultural transmission

Nature Communications, 2023
Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. It can be thought of as the process that perpetuates fit variants in cultural evolution.
Avishkar Bhoopchand, Bethanie Brownfield, Adrian Collister, Agustin Dal Lago, Ashley Edwards, Richard Everett, Alexandre Fréchette, Yanko Gitahy Oliveira, Edward Hughes, Kory W. Mathewson, Piermaria Mendolicchio, Julia Pawar, Miruna Pȋslar, Alex Platonov, Evan Senter, Sukhdeep Singh, Alexander Zacherl, Lei M. Zhang   +17 more
doaj   +1 more source

Few-Shot Classification with Contrastive Learning

, 2022
To appear in ECCV ...
Zhanyuan Yang, Jinghua Wang, Yingying Zhu 0001   +2 more
openaire   +2 more sources

Few-Shot Partial-Label Learning [PDF]

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021
Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of existing PLL solutions is that there are sufficient partial-label (PL) samples for training.
Yunfeng Zhao, Guoxian Yu, Lei Liu 0003, Zhongmin Yan, Lizhen Cui, Carlotta Domeniconi   +5 more
openaire   +2 more sources

Few-Shot Class-Incremental Learning [PDF]

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the ...
Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei 0001, Yihong Gong   +5 more
openaire   +2 more sources

Adaptive Learning Knowledge Networks for Few-Shot Learning

IEEE Access, 2019
In recent years, relying on training with thousands of labeled samples, deep learning has achieved remarkable success in the field of computer vision. However, in practice, annotating samples is a time-consuming and laborious task, which means that it is
Minghao Yan
doaj   +1 more source

VEHICLE DETECTION AND IDENTIFICATION WITH SMALL DATASET USING FEW-SHOT LEARNING

International Journal of Advances in Signal and Image Sciences, 2023
Vehicle detection and identification serve an important role in employing autonomous vehicle classification. However, most deep learning methods for vehicle detection rely on large number of datasets for the training to perform well. The dataset shortage
Muzakki Afandi, Media Anugerah Ayu
doaj   +1 more source

Robust Compare Network for Few-Shot Learning

IEEE Access, 2020
Making machines learn like humans is the ultimate goal of artificial intelligence. Few-shot learning attempts to simulate the learning mechanism of humans, which is a task that can learn novel concepts from very few labeled samples.
Yixin Yang, Yang Li, Rui Zhang, Jiabao Wang, Zhuang Miao   +4 more
doaj   +1 more source

Generative knowledge-based transfer learning for few-shot health condition estimation

Complex & Intelligent Systems, 2022
In the field of high-end manufacturing, it is valuable to study few-shot health condition estimation. Although transfer learning and other methods have effectively improved the ability of few-shot learning, they still cannot solve the lack of prior ...
Weijie Kang, Jiyang Xiao, Junjie Xue
doaj   +1 more source