English
Related papers

Related papers: Information-theoretic Semi-supervised Metric Learn…

200 papers

Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose…

Machine Learning · Computer Science 2019-10-22 Alexander Genkin , Anirvan M. Sengupta , Dmitri Chklovskii

Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in…

Machine Learning · Computer Science 2020-08-19 Lifeng Gu

Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…

Machine Learning · Statistics 2022-08-09 Jonathan Richard Schwarz , Yee Whye Teh

State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. An inherent drawback of this strategy stems from the quality of the…

Machine Learning · Computer Science 2024-03-26 Shambhavi Mishra , Balamurali Murugesan , Ismail Ben Ayed , Marco Pedersoli , Jose Dolz

A number of machine learning algorithms are using a metric, or a distance, in order to compare individuals. The Euclidean distance is usually employed, but it may be more efficient to learn a parametric distance such as Mahalanobis metric.…

Machine Learning · Computer Science 2016-12-16 Hoel Le Capitaine

Supervised manifold learning methods learn data representations by preserving the geometric structure of data while enhancing the separation between data samples from different classes. In this work, we propose a theoretical study of…

Machine Learning · Computer Science 2018-01-08 Elif Vural , Christine Guillemot

Semi-supervised Laplacian regularization, a standard graph-based approach for learning from both labelled and unlabelled data, was recently demonstrated to have an insignificant high dimensional learning efficiency with respect to…

Machine Learning · Computer Science 2020-06-16 Xiaoyi Mai , Romain Couillet

In this paper we consider the problem of semi-supervised learning with deep Convolutional Neural Networks (ConvNets). Semi-supervised learning is motivated on the observation that unlabeled data is cheap and can be used to improve the…

Computer Vision and Pattern Recognition · Computer Science 2016-06-13 Mehdi Sajjadi , Mehran Javanmardi , Tolga Tasdizen

Event-based semantic segmentation has gained popularity due to its capability to deal with scenarios under high-speed motion and extreme lighting conditions, which cannot be addressed by conventional RGB cameras. Since it is hard to…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Linglin Jing , Yiming Ding , Yunpeng Gao , Zhigang Wang , Xu Yan , Dong Wang , Gerald Schaefer , Hui Fang , Bin Zhao , Xuelong Li

In this paper, we propose a novel graph-based approach for semi-supervised learning problems, which considers an adaptive adjacency of the examples throughout the unsupervised portion of the training. Adjacency of the examples is inferred…

Machine Learning · Computer Science 2020-08-06 Ozsel Kilinc , Ismail Uysal

Graph-based methods play an important role in unsupervised and semi-supervised learning tasks by taking into account the underlying geometry of the data set. In this paper, we consider a statistical setting for semi-supervised learning and…

Machine Learning · Computer Science 2015-02-17 Aamir Anis , Aly El Gamal , A. Salman Avestimehr , Antonio Ortega

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are…

Consider semi-supervised learning for classification, where both labeled and unlabeled data are available for training. The goal is to exploit both datasets to achieve higher prediction accuracy than just using labeled data alone. We…

Machine Learning · Statistics 2019-06-20 Xinwei Zhang , Zhiqiang Tan

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

Machine Learning · Computer Science 2019-03-25 Kyle Hsu , Sergey Levine , Chelsea Finn

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Mahmoud Assran , Mathilde Caron , Ishan Misra , Piotr Bojanowski , Armand Joulin , Nicolas Ballas , Michael Rabbat

In this work, we used a semi-supervised learning method to train deep learning model that can segment the brain MRI images. The semi-supervised model uses less labeled data, and the performance is competitive with the supervised model with…

Image and Video Processing · Electrical Eng. & Systems 2022-12-07 Hedong Zhang , Anand A. Joshi

The recently proposed self-ensembling methods have achieved promising results in deep semi-supervised learning, which penalize inconsistent predictions of unlabeled data under different perturbations. However, they only consider adding…

Machine Learning · Computer Science 2018-03-29 Yucen Luo , Jun Zhu , Mengxi Li , Yong Ren , Bo Zhang

Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been…

Machine Learning · Statistics 2019-10-25 Xiuming Liu , Dave Zachariah , Johan Wågberg , Thomas B. Schön

Probabilistic embeddings have several advantages over deterministic embeddings as they map each data point to a distribution, which better describes the uncertainty and complexity of data. Many works focus on adjusting the distribution…

Artificial Intelligence · Computer Science 2024-12-16 Xiang Huang , Hao Peng , Li Sun , Hui Lin , Chunyang Liu , Jiang Cao , Philip S. Yu

Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done…

Information Theory · Computer Science 2018-12-27 Yaniv Fogel , Meir Feder