paper-with-me

Papers

Combining self-labeling and demand based active learning for non-stationary data streams

2023-02-08 · Valerie Vaquet, Fabian Hinder, Johannes Brinkrolf, Barbara Hammer

Learning from non-stationary data streams is a research direction that gains increasing interest as more data in form of streams becomes available, for example from social media, smartphones, or industrial process monitoring. Most approaches assume that the ground truth of the samples becomes available (possibly with some delay) and perform supervised online learning in the test-then-train scheme. While this assumption might be valid in some scenarios, it does not apply to all settings. In this work, we focus on scarcely labeled data streams and explore the potential of self-labeling in gradually drifting data streams. We formalize this setup and propose a novel online $k$-nn classifier that combines self-labeling and demand-based active learning.

📄 PDF Abstract BibTeX arXiv:2302.04141

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learningvalid

Similar Papers 제목 키워드 기반

Combining Self-labeling with Selective Sampling

2023-01-11 · Jędrzej Kozal, Michał Woźniak

Since data is the fuel that drives machine learning models, and access to labeled data is generally expensive, semi-supervised methods are constantly popular. They enable the acquisition of large datasets without the nee…

Active Learning

Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition

2023-08-28 · Zhisheng Zheng, Ziyang Ma, Yu Wang, Xie Chen

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuni…

Active LearningAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learning+2

A Histopathology Study Comparing Contrastive Semi-Supervised and Fully Supervised Learning

2021-11-10 · Lantian Zhang, Mohamed Amgad, Lee A. D. Cooper

Data labeling is often the most challenging task when developing computational pathology models. Pathologist participation is necessary to generate accurate labels, and the limitations on pathologist time and demand for …

Active LearningSelf-Supervised LearningWeakly-supervised Learning

Reducing Label Effort: Self-Supervised meets Active Learning

2021-08-25 · Javad Zolfaghari Bengar, Joost Van de Weijer, Bartlomiej Twardowski, Bogdan Raducanu

Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-trainin…

Active LearningObject Recognition

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision

2020-03-01 · CVPR 2020 6 · Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Sotaro Tsukizawa

Active learning (AL) aims to minimize labeling efforts for data-demanding deep neural networks (DNNs) by selecting the most representative data points for annotation. However, currently used methods are ill-equipped to d…

Active LearningPseudo Label