中文
相关论文

相关论文: DEUCE: Dual-diversity Enhancement and Uncertainty-…

200 篇论文

Recently, Deep Neural Networks (DNNs) have made remarkable progress for text classification, which, however, still require a large number of labeled data. To train high-performing models with the minimal annotation cost, active learning is…

计算与语言 · 计算机科学 2021-08-25 Qiang Liu , Yanqiao Zhu , Zhaocheng Liu , Yufeng Zhang , Shu Wu

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label new selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due…

机器学习 · 计算机科学 2024-07-16 Dongyuan Li , Zhen Wang , Yankai Chen , Renhe Jiang , Weiping Ding , Manabu Okumura

Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…

计算与语言 · 计算机科学 2020-07-22 Haw-Shiuan Chang , Shankar Vembu , Sunil Mohan , Rheeya Uppaal , Andrew McCallum

Active learning (AL) is an effective approach to select the most informative samples to label so as to reduce the annotation cost. Existing AL methods typically work under the closed-set assumption, i.e., all classes existing in the…

计算机视觉与模式识别 · 计算机科学 2023-07-12 Linhao Qu , Yingfan Ma , Zhiwei Yang , Manning Wang , Zhijian Song

In the active learning paradigm, using an oracle to label data has always been a complex and expensive task, and with the emersion of large unlabeled data pools, it would be highly beneficial If we could achieve better results without…

机器学习 · 计算机科学 2025-08-12 Hadi Khorsand , Vahid Pourahmadi

The existing active learning methods select the samples by evaluating the sample's uncertainty or its effect on the diversity of labeled datasets based on different task-specific or model-specific criteria. In this paper, we propose the…

机器学习 · 计算机科学 2021-08-24 Zhuoming Liu , Hao Ding , Huaping Zhong , Weijia Li , Jifeng Dai , Conghui He

In image classification tasks, the ability of deep CNNs to deal with complex image data has proven to be unrivalled. However, they require large amounts of labeled training data to reach their full potential. In specialised domains such as…

机器学习 · 计算机科学 2018-11-12 Remus Pop , Patric Fulop

Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existing knowledge bases with snippets in the text but suffer from…

计算与语言 · 计算机科学 2025-07-04 Shuzheng Si , Helan Hu , Haozhe Zhao , Shuang Zeng , Kaikai An , Zefan Cai , Baobao Chang

Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even…

Purpose: Manual annotations for training deep learning (DL) models in auto-segmentation are time-intensive. This study introduces a hybrid representation-enhanced sampling strategy that integrates both density and diversity criteria within…

图像与视频处理 · 电气工程与系统科学 2023-12-21 Ganping Li , Yoshito Otake , Mazen Soufi , Masashi Taniguchi , Masahide Yagi , Noriaki Ichihashi , Keisuke Uemura , Masaki Takao , Nobuhiko Sugano , Yoshinobu Sato

Cold-Start Active Learning (CSAL) aims to select informative samples for annotation without prior knowledge, which is important for improving annotation efficiency and model performance under a limited annotation budget in medical image…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Ning Zhu , Xiaochuan Ma , Shaoting Zhang , Guotai Wang

The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expensive. Active learning is a research area that addresses the…

计算机视觉与模式识别 · 计算机科学 2022-07-26 Felix Buchert , Nassir Navab , Seong Tae Kim

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

计算机视觉与模式识别 · 计算机科学 2022-09-12 Fan Yang , Kai Wu , Shuyi Zhang , Guannan Jiang , Yong Liu , Feng Zheng , Wei Zhang , Chengjie Wang , Long Zeng

The laborious process of labeling data often bottlenecks projects that aim to leverage the power of supervised machine learning. Active Learning (AL) has been established as a technique to ameliorate this condition through an iterative…

机器学习 · 计算机科学 2022-03-18 Trent J. Bradberry , Christopher H. Hase , LeAnna Kent , Joel A. Góngora

During recent years, active learning has evolved into a popular paradigm for utilizing user's feedback to improve accuracy of learning algorithms. Active learning works by selecting the most informative sample among unlabeled data and…

机器学习 · 计算机科学 2016-11-17 Alireza Ghasemi , Hamid R. Rabiee , Mohsen Fadaee , Mohammad T. Manzuri , Mohammad H. Rohban

Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. This benefits especially deep neural networks which generally require a huge number of…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Jihyo Kim , Jeonghyeon Kim , Sangheum Hwang

This work introduces Dirichlet Active Learning (DiAL), a Bayesian-inspired approach to the design of active learning algorithms. Our framework models feature-conditional class probabilities as a Dirichlet random field and lends…

机器学习 · 统计学 2023-11-10 Kevin Miller , Ryan Murray

While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data for labeling and…

机器学习 · 计算机科学 2022-07-20 Xueying Zhan , Qingzhong Wang , Kuan-hao Huang , Haoyi Xiong , Dejing Dou , Antoni B. Chan

In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. However, training two networks with a set of noisy pseudo…

计算机视觉与模式识别 · 计算机科学 2022-10-10 Zeqi Chen , Zhichao Cui , Chi Zhang , Jiahuan Zhou , Yuehu Liu

Positive-Unlabeled (PU) learning aims to learn a model with rare positive samples and abundant unlabeled samples. Compared with classical binary classification, the task of PU learning is much more challenging due to the existence of many…

计算机视觉与模式识别 · 计算机科学 2022-12-01 Chengming Xu , Chen Liu , Siqian Yang , Yabiao Wang , Shijie Zhang , Lijie Jia , Yanwei Fu