Results 31 to 40 of about 822,037 (305)
, 2022 The DARPA Lifelong Learning Machines (L2M) program seeks to yield advances in artificial intelligence (AI) systems so that they are capable of learning (and improving) continuously, leveraging data on one task to improve performance on another, and doing so in a computationally sustainable way.
New, Alexander +3 more
openaire +2 more sources
RecFRCN: Few-Shot Object Detection With Recalibrated Faster R-CNN
IEEE Access, 2023 Currently, Faster R-CNN serves as the fundamental detection framework in the majority of few-shot object detection algorithms. However, due to limited samples per class, the Faster R-CNN’s classification branch faces limitations in capturing ...
Youyou Zhang, Tongwei Lu
doaj +1 more source
Distributed Semi-Supervised Metric Learning
IEEE Access, 2016 Over the last decade, many pairwise-constraint-based metric learning algorithms have been developed to automatically learn application-specific metrics from data under similarity/dissimilarity data-pair constraints (weak labels).
Pengcheng Shen, Xin Du, Chunguang Li
doaj +1 more source
MLMD: Metric Learning for Predicting MiRNA-Disease Associations
IEEE Access, 2021 The crucial roles played by microRNAs (miRNAs) in regulating various biological functions and in disease incidence have been reported continuously over the past decades.
Jihwan Ha, Chihyun Park
doaj +1 more source
Hardness-Aware Deep Metric Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 This paper presents a hardness-aware deep metric learning (HDML) framework for image clustering and retrieval. Most existing deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training.
Wenzhao Zheng, Jiwen Lu, Jie Zhou
openaire +2 more sources
Wi-Fi-Based Location-Independent Human Activity Recognition via Meta Learning
Sensors, 2021 Wi-Fi-based device-free human activity recognition has recently become a vital underpinning for various emerging applications, ranging from the Internet of Things (IoT) to Human–Computer Interaction (HCI).
Xue Ding +4 more
doaj +1 more source
Adversarial Metric Learning [PDF]
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018 In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However, the trained models often fail to produce reliable distances on the ambiguous test pairs due to the different ...
Chen, Shuo +5 more
openaire +2 more sources
metric-learn: Metric Learning Algorithms in Python
, 2019 metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms. As part of scikit-learn-contrib, it provides a unified interface compatible with scikit-learn which allows to easily perform cross-validation, model selection, and pipelining with other machine learning estimators.
de Vazelhes, William +4 more
openaire +3 more sources
Attribute-enhanced metric learning for face retrieval
EURASIP Journal on Image and Video Processing, 2018 Metric learning is a significant factor for media retrieval. In this paper, we propose an attribute label enhanced metric learning model to assist face image retrieval.
Yuchun Fang, Qiulong Yuan
doaj +1 more source
Enhancing Metric-Based Few-Shot Classification With Weighted Large Margin Nearest Center Loss
IEEE Access, 2021 Metric-learning-based methods, which attempt to learn a deep embedding space on extremely large episodes, have been successfully applied to few-shot classification problems.
Wei Bao, Meiyu Huang, Xueshuang Xiang
doaj +1 more source