Skip to Content

638 Results Found

  • Article
  • Open Access
5 Citations
1,523 Views
16 Pages

16 November 2025

Edge detection is critical in various computer vision applications such as object recognition, segmentation, and scene understanding. The Canny edge detector remains widely used in traditional methods due to its balance between accuracy and computati...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Feature Paper
  • Article
  • Open Access
2,272 Views
17 Pages

Progressive Training Technique with Weak-Label Boosting for Fine-Grained Classification on Unbalanced Training Data

  • Yuhui Jin,
  • Zuyun Wang,
  • Huimin Liao,
  • Sainan Zhu and ,
  • Bin Tong,
  • Yu Yin and
  • Jian Huang
  • + 2 authors+ 0 author

In practical classification tasks, the sample distribution of the dataset is often unbalanced; for example, this is the case in a dataset that contains a massive quantity of samples with weak labels and for which concrete identification is unavailabl...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
5 Citations
1,430 Views
23 Pages

2 March 2026

Deep time-series forecasting models can achieve strong average accuracy under normal conditions, yet they often struggle with rare, high-impact extremes, where severe class imbalance biases learning toward majority dynamics. Although infrequent, thes...

(This article belongs to the Special Issue Sensors in 2026)
  • Article
  • Open Access
8 Citations
6,354 Views
18 Pages

Rule-Enhanced Active Learning for Semi-Automated Weak Supervision

  • David Kartchner,
  • Davi Nakajima An,
  • Wendi Ren,
  • Chao Zhang and
  • Cassie S. Mitchell

16 March 2022

A major bottleneck preventing the extension of deep learning systems to new domains is the prohibitive cost of acquiring sufficient training labels. Alternatives such as weak supervision, active learning, and fine-tuning of pretrained models reduce t...

(This article belongs to the Topic Methods for Data Labelling for Intelligent Systems)
  • Article
  • Open Access
349 Views
35 Pages

7 September 2026

Multi-label classification of financial news is frequently affected by incomplete and noisy annotations, while obtaining expert-curated labels at scale is prohibitively expensive. This study proposes a weakly supervised classification framework that...

(This article belongs to the Special Issue Advances in Weakly Supervised Learning: Theories, Algorithms, and Applications)
  • Article
  • Open Access
273 Views
23 Pages

17 September 2026

Sentiment classification often relies on costly in-domain annotations, while weak-supervision sources provide low-cost but inconsistent labels. We propose Multi-Source Reliability-Aware Aggregation and Cross-domain Consistency Learning (MSRA-CCL) for...

  • Article
  • Open Access
943 Views
14 Pages

Weakly Supervised MRI-Based Classification of Alzheimer’s Disease Using Clinical Pseudo-Labels

  • Rong Xiao,
  • Tingwei Quan,
  • Xinglong Wu,
  • Guoping Xu and
  • Shangbin Chen

24 August 2026

Alzheimer’s disease (AD) classification from structural magnetic resonance imaging (MRI) may benefit from weak supervision that uses clinically meaningful but imperfect supervisory signals. We evaluated a weakly supervised framework in which a...

  • Article
  • Open Access
7 Citations
5,964 Views
26 Pages

25 June 2023

Emotion detection in text is a fundamental aspect of affective computing and is closely linked to natural language processing. Its applications span various domains, from interactive chatbots to marketing and customer service. This research specifica...

(This article belongs to the Special Issue Natural Language Processing (NLP) and Applications)
  • Article
  • Open Access
1,456 Views
19 Pages

30 January 2026

Ensuring that Large Language Models align with human values of honesty is a critical challenge, particularly due to the scarcity of labeled data for distinguishing known versus unknown knowledge boundaries. We propose a weak-to-strong generalization...

(This article belongs to the Special Issue AI, Machine Learning and Optimization)
  • Article
  • Open Access
98 Citations
6,220 Views
17 Pages

30 September 2021

Yellow rust is a disease with a wide range that causes great damage to wheat. The traditional method of manually identifying wheat yellow rust is very inefficient. To improve this situation, this study proposed a deep-learning-based method for identi...

(This article belongs to the Section Sensors and Robotics)
  • Article
  • Open Access
7 Citations
4,413 Views
14 Pages

The Kuwaiti dialect is a particular dialect of Arabic spoken in Kuwait; it differs significantly from standard Arabic and the dialects of neighboring countries in the same region. Few research papers with a focus on the Kuwaiti dialect have been publ...

  • Article
  • Open Access
8 Citations
3,379 Views
19 Pages

20 October 2022

Field seed maturity monitoring is essential to optimize the farming process and guarantee yield quality through high germination. Remote sensing of parsley fields through UAV multispectral imagery allows uniform scanning and better capture of crop in...

(This article belongs to the Special Issue Synergy of UAV Imagery and Artificial Intelligence for Agriculture)
  • Article
  • Open Access
16 Citations
3,276 Views
15 Pages

20 June 2022

The transition from the quantum to the classical world is not yet understood. Here, we take a new approach. Central to this is the understanding that measurement and actualization cannot occur except on some specific basis. However, we have no establ...

  • Article
  • Open Access
9 Citations
2,424 Views
23 Pages

9 November 2022

The previous multi-frame version of the generalized labeled multi-Bernoulli model (MF-GLMB) only accounts for standard measurement models. It is not suitable for application in the detection and tracking of multiple weak targets (low signal-to-noise...

  • Article
  • Open Access
714 Views
23 Pages

Frugal Learning Methods for Kidney Segmentation in Non-Contrast MRI

  • Jan Podlaszewski,
  • Artur Klepaczko,
  • Ludomir Stefańczyk and
  • Marcin Majos

22 July 2026

Background/Objectives: Chronic kidney disease is a growing global health concern, necessitating effective tools for early detection and monitoring. While non-contrast T1-weighted magnetic resonance imaging offers a non-invasive means to assess kidney...

(This article belongs to the Section Nephrology & Urology)
  • Article
  • Open Access
7 Citations
1,449 Views
26 Pages

8 April 2026

Kazakh sequence labeling is constrained by limited annotated resources, while its agglutinative morphology and productive suffixation increase data sparsity and exacerbate label inconsistency in part-of-speech (POS) tagging and named entity recogniti...

(This article belongs to the Special Issue Advancements in Large Language Models Applied in Multidisciplinary Research Contexts)
  • Article
  • Open Access
7 Citations
2,081 Views
20 Pages

1 October 2025

Manual pixel-level annotation remains a major bottleneck in deploying deep learning models for dense prediction and semantic segmentation tasks across domains. This challenge is especially pronounced in applications involving fine-scale structures, s...

(This article belongs to the Special Issue Advanced Machine Learning, Pattern Recognition, and Deep Learning Technologies: Methodologies and Applications, 2nd Edition)
  • Article
  • Open Access
332 Views
18 Pages

BoxGuide: Exploring Weakly-Supervised Instance Segmentation for Acne Lesions Inspired by Reinforcement Learning

  • Xin Wei,
  • Zhirong Tang,
  • Jian Zhang,
  • Lingyun Zhang and ,
  • Junyang Cao,
  • Hong Yang and
  • Jinbo Huang
  • + 2 authors+ 0 author

28 September 2026

Neural network-based instance segmentation methods are essential for the automated diagnosis of patients with acne. However, a lack of pixel-wise annotations, which are time-consuming and labor-intensive to generate, severely impedes the development...

(This article belongs to the Special Issue Reinforcement Learning: Emerging Techniques and Future Prospects)
  • Article
  • Open Access
5 Citations
4,043 Views
18 Pages

26 August 2022

In this paper, we propose the specific recursion formula for the generalized labeled multi-Bernoulli filter based on the track-before-detect strategy (GLMB-TBD) using a belief propagation algorithm. The proposed method aims to track multiple weak tar...

  • Article
  • Open Access
366 Views
23 Pages

25 July 2026

Indoor temperature forecasting in large public buildings is affected by heating, ventilation, and air-conditioning (HVAC) control, occupancy, airflow, and zone use, not only by recent temperature histories. This study asks whether operationally deriv...

(This article belongs to the Special Issue From Automation to Intelligence: Enhancing Energy Performance of HVAC Systems)
  • Article
  • Open Access
325 Views
30 Pages

12 August 2026

Segmenting human skin regions in digital images is a well-studied computer vision problem with a wide range of applications. State-of-the-art deep learning models achieve high accuracy, but their training requires large sets of precisely annotated pi...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
42 Citations
12,231 Views
42 Pages

14 September 2012

According to existing literature and despite their commercial success, state-of-the-art two-stage non-iterative geographic object-based image analysis (GEOBIA) systems and three-stage iterative geographic object-oriented image analysis (GEOOIA) syste...

  • Article
  • Open Access
20 Citations
11,359 Views
50 Pages

20 September 2012

According to literature and despite their commercial success, state-of-the-art two-stage non-iterative geographic object-based image analysis (GEOBIA) systems and three-stage iterative geographic object-oriented image analysis (GEOOIA) systems, where...

  • Data Descriptor
  • Open Access
11 Citations
6,148 Views
16 Pages

A Semantically Annotated 15-Class Ground Truth Dataset for Substation Equipment to Train Semantic Segmentation Models

  • Andreas Anael Pereira Gomes,
  • Francisco Itamarati Secolo Ganacim,
  • Fabiano Gustavo Silveira Magrin,
  • Nara Bobko and ,
  • Leonardo Göbel Fernandes,
  • Anselmo Pombeiro and
  • Eduardo Félix Ribeiro Romaneli
  • + 2 authors+ 0 author

5 July 2023

The lack of annotated semantic segmentation datasets for electrical substations in the literature poses a significant problem for machine learning tasks; before training a model, a dataset is needed. This paper presents a new dataset of electric subs...

(This article belongs to the Topic Methods for Data Labelling for Intelligent Systems)
  • Article
  • Open Access
22 Citations
3,685 Views
22 Pages

Weakly Supervised Perennial Weed Detection in a Barley Field

  • Leon-Friedrich Thomas,
  • Mikael Änäkkälä and
  • Antti Lajunen

1 June 2023

In the field of precision agriculture, weed detection models combined with selective spraying by ground or aerial robotics are seen as promising approaches for increasing yield harvests while simultaneously minimizing herbicide use. The available lab...

(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)
  • Article
  • Open Access
5 Citations
2,890 Views
20 Pages

Expand and Shrink: Federated Learning with Unlabeled Data Using Clustering

  • Ajit Kumar,
  • Ankit Kumar Singh,
  • Syed Saqib Ali and
  • Bong Jun Choi

25 November 2023

The amalgamation of the Internet of Things (IoT) and federated learning (FL) is leading the next generation of data usage due to the possibility of deep learning with data privacy preservation. The FL architecture currently assumes labeled data sampl...

(This article belongs to the Special Issue Federated and Distributed Learning in IoT)
  • Article
  • Open Access
2 Citations
1,883 Views
19 Pages

Pedestrian Re-Identification Based on Weakly Supervised Multi-Feature Fusion

  • Changming Qin,
  • Zhiwen Wang,
  • Linghui Zhang,
  • Qichang Peng and ,
  • Guixing Lin and
  • Guanlin Lu
  • + 1 author+ 0 author

24 September 2024

This article proposes a weakly supervised multi-feature fusion pedestrian re-identification method, which introduces a multi-feature fusion mechanism to extract feature information from different layers into the same feature space and fuse them into...

(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
  • Article
  • Open Access
11 Citations
4,012 Views
18 Pages

JMLNet: Joint Multi-Label Learning Network for Weakly Supervised Semantic Segmentation in Aerial Images

  • Rongxin Guo,
  • Xian Sun,
  • Kaiqiang Chen,
  • Xiao Zhou and ,
  • Zhiyuan Yan,
  • Wenhui Diao and
  • Menglong Yan
  • + 2 authors+ 0 author

27 September 2020

Weakly supervised semantic segmentation in aerial images has attracted growing research attention due to the significant saving in annotation cost. Most of the current approaches are based on one specific pseudo label. These methods easily overfit th...

(This article belongs to the Section AI Remote Sensing)
  • Article
  • Open Access
1 Citations
536 Views
20 Pages

A Hierarchical Graph Neural Network with Cross-Layer Attention for Weak-Node Identification in Complex Interconnected Power Grids

  • Fan Li,
  • Zhe Zhang,
  • Jishuo Qin,
  • Zhidong Wang and ,
  • Taikun Tao and
  • Libo Zhang
  • + 1 author+ 0 author

25 May 2026

Accurate identification of weak nodes is a prerequisite for online security assessment, preventive control, and resilience enhancement in modern power systems. However, conventional single-layer graph-learning models mainly emphasize local neighborho...

(This article belongs to the Section F1: Electrical Power System)
  • Brief Report
  • Open Access
3 Citations
3,490 Views
8 Pages

MISM: A Medical Image Segmentation Metric for Evaluation of Weak Labeled Data

  • Dennis Hartmann,
  • Verena Schmid,
  • Philip Meyer,
  • Florian Auer and ,
  • Iñaki Soto-Rey,
  • Dominik Müller and
  • Frank Kramer
  • + 2 authors+ 0 author

Performance measures are an important tool for assessing and comparing different medical image segmentation algorithms. Unfortunately, the current measures have their weaknesses when it comes to assessing certain edge cases. These limitations arise w...

(This article belongs to the Special Issue Deep Learning for Medical Imaging Diagnosis)
  • Article
  • Open Access
4 Citations
5,062 Views
13 Pages

22 November 2022

Semi-supervised object detection algorithms based on the self-training paradigm produce pseudo bounding boxes with unavoidable noise. We propose a semi-supervised object detection algorithm based on teacher-student models with strong-weak heads to co...

  • Article
  • Open Access
1 Citations
1,800 Views
15 Pages

8 February 2025

We investigate the detectability verification problem of time-dependent systems modeled by time labeled Petri nets that are a typical time-dependent model of many computer-integrated systems in modern society, characterized by networked connections....

(This article belongs to the Topic Modeling, Stability, and Control of Dynamic Systems and Their Applications)
  • Article
  • Open Access
81 Views
21 Pages

18 November 2026

Deep learning cloud detectors require large volumes of pixel-level labels that are expensive to produce. Gridded cloud cover from ERA5 reanalysis and GFS forecasts could serve as freely available weak supervision. We assess this hypothesis through a...

(This article belongs to the Special Issue Deep Learning-Based Image Processing, Analysis and Reconstruction Technology)
  • Article
  • Open Access
1 Citations
2,599 Views
16 Pages

19 September 2024

Semi-supervised medical image segmentation models often face challenges such as empirical mismatch and data imbalance. Traditional methods, like the two-stream perturbation model, tend to over-rely on strong perturbation, leaving weak perturbation an...

  • Article
  • Open Access
8 Citations
3,791 Views
19 Pages

25 November 2022

Robust maritime obstacle detection is critical for safe navigation of autonomous boats and timely collision avoidance. The current state-of-the-art is based on deep segmentation networks trained on large datasets. However, per-pixel ground truth labe...

(This article belongs to the Section Vehicular Sensing)
  • Article
  • Open Access
256 Citations
25,096 Views
25 Pages

Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery

  • Sherrie Wang,
  • William Chen,
  • Sang Michael Xie,
  • George Azzari and
  • David B. Lobell

7 January 2020

Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve sta...

(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)
  • Article
  • Open Access
1 Citations
729 Views
21 Pages

SwinMR: A Mutual Refinement Enhanced SwinTrack Framework

  • Shifeng Zhao,
  • Chuanyuan Yang and
  • Yanfang Fu

11 December 2025

The task of tracking weak targets in low-altitude UAV scenarios requires high robustness and generalization ability of the model. Against this backdrop, this paper proposes a novel annotation and training mechanism based on SwinTrack. To improve the...

  • Article
  • Open Access
11 Citations
4,387 Views
16 Pages

19 March 2021

We performed a laboratory study in France to explore consumer reactions to information about lentils, a legume whose consumption is sustainable and recommended by nutritionists and environmentalists. More specifically, we examined the effect of infor...

(This article belongs to the Section Economic and Business Aspects of Sustainability)
  • Article
  • Open Access
25 Citations
6,418 Views
16 Pages

Automatic Detection of Chewing and Swallowing

  • Akihiro Nakamura,
  • Takato Saito,
  • Daizo Ikeda,
  • Ken Ohta and ,
  • Hiroshi Mineno and
  • Masafumi Nishimura
  • + 1 author+ 0 author

12 May 2021

A series of eating behaviors, including chewing and swallowing, is considered to be crucial to the maintenance of good health. However, most such behaviors occur within the human body, and highly invasive methods such as X-rays and fiberscopes must b...

(This article belongs to the Special Issue Acoustic Event Detection and Sensing)
  • Article
  • Open Access
10 Citations
2,854 Views
26 Pages

8 February 2025

Due to the challenge of acquiring abundant labeled samples, semi-supervised change detection (SSCD) approaches are becoming increasingly popular in tackling CD tasks with limited labeled data. Despite their success, these methods tend to come with co...

(This article belongs to the Section Satellite Missions for Earth and Planetary Exploration)
  • Article
  • Open Access
9 Citations
3,073 Views
22 Pages

10 July 2024

Radar jamming recognition is a key step in electronic countermeasures, and accurate and sufficient labeled samples are essential for supervised learning-based recognition methods. However, in real practice, collected radar jamming samples often have...

(This article belongs to the Topic Radar Signal and Data Processing with Applications)
  • Article
  • Open Access
21 Citations
6,994 Views
15 Pages

Switching of Photocatalytic Tyrosine/Histidine Labeling and Application to Photocatalytic Proximity Labeling

  • Keita Nakane,
  • Haruto Nagasawa,
  • Chizu Fujimura,
  • Eri Koyanagi and ,
  • Shusuke Tomoshige,
  • Minoru Ishikawa and
  • Shinichi Sato
  • + 2 authors+ 0 author

2 October 2022

Weak and transient protein interactions are involved in dynamic biological responses and are an important research subject; however, methods to elucidate such interactions are lacking. Proximity labeling is a promising technique for labeling transien...

(This article belongs to the Collection Feature Papers Collection in Biochemistry)
  • Article
  • Open Access
5 Citations
2,110 Views
24 Pages

A Weak Sample Optimisation Method for Building Classification in a Semi-Supervised Deep Learning Framework

  • Yanjun Wang,
  • Yunhao Lin,
  • Huiqing Huang,
  • Shuhan Wang and ,
  • Shicheng Wen and
  • Hengfan Cai
  • + 1 author+ 0 author

8 September 2023

Deep learning has gained widespread interest in the task of building semantic segmentation modelling using remote sensing images; however, neural network models require a large number of training samples to achieve better classification performance,...

(This article belongs to the Special Issue Advances in Object and Activity Detection in Remote Sensing Imagery II)
  • Article
  • Open Access
8 Citations
5,652 Views
22 Pages

17 July 2023

We propose a fully automatic annotation scheme that takes a raw 3D point cloud with a set of fitted CAD models as input and outputs convincing point-wise labels that can be used as cheap training data for point cloud segmentation. Compared with manua...

(This article belongs to the Special Issue New Perspectives on 3D Point Cloud)
  • Article
  • Open Access
2 Citations
4,469 Views
22 Pages

Business Friendliness: A Double-Edged Sword

  • Mengyin Li,
  • Phillip H. Phan and
  • Xian Sun

8 February 2021

In this paper, we test the hypothesis that business-friendly local-government policies combined with weak legal institutions lead to lower economic welfare in the form of greater fraud activity. Using data of almost 3000 failed peer-to-peer (P2P) len...

(This article belongs to the Special Issue Harnessing Sustainability to Corporate Finance and Financial Institutions)
  • Article
  • Open Access
1 Citations
912 Views
28 Pages

Semi-Supervised Change Detection for High-Resolution Remote Sensing Images Based on Label Extension

  • Shuo Liu,
  • Li Wan,
  • Fei Xie,
  • Xinlong Shu and ,
  • Yaxin Lei and
  • Wuxia Zhang
  • + 1 author+ 0 author

29 May 2026

Change detection (CD) refers to the analysis of changes in the utilization of land, buildings, and other targets in the same surface environment using relevant technologies and remote sensing images. Although deep learning-based change detection meth...

(This article belongs to the Special Issue Robust Perception in Open and Data-Limited Environments: From Earth to Deep Space)
  • Article
  • Open Access
27 Citations
6,318 Views
25 Pages

29 April 2021

The problem of automatic detection of fake news in social media, e.g., on Twitter, has recently drawn some attention. Although, from a technical perspective, it can be regarded as a straight-forward, binary classification problem, the major challenge...

(This article belongs to the Special Issue Digital and Social Media in the Disinformation Age)
  • Article
  • Open Access
3 Citations
3,866 Views
15 Pages

Mixup Based Cross-Consistency Training for Named Entity Recognition

  • Geonsik Youn,
  • Bohan Yoon,
  • Seungbin Ji,
  • Dahee Ko and
  • Jongtae Rhee

1 November 2022

Named Entity Recognition (NER) is at the core of natural language understanding. The quality and amount of datasets determine the performance of deep-learning-based NER models. As datasets for NER require token-level or word-level labels to be assign...

(This article belongs to the Special Issue Natural Language Processing (NLP) and Applications)
  • Article
  • Open Access
2 Citations
2,826 Views
18 Pages

An Effective Multi-Label Feature Selection Model Towards Eliminating Noisy Features

  • Jun Wang,
  • Yuanyuan Xu,
  • Hengpeng Xu,
  • Zhe Sun and ,
  • Zhenglu Yang and
  • Jinmao Wei
  • + 1 author+ 0 author

15 November 2020

Feature selection has devoted a consistently great amount of effort to dimension reduction for various machine learning tasks. Existing feature selection models focus on selecting the most discriminative features for learning targets. However, this s...

(This article belongs to the Special Issue Machine Learning Methods with Noisy, Incomplete or Small Datasets)
  • Article
  • Open Access
2 Citations
3,846 Views
11 Pages

A Differential Detection Method Based on a Linear Weak Measurement System

  • Nian Xiong,
  • Tian Guan,
  • Yang Xu,
  • Lixuan Shi and ,
  • Suyi Zhong,
  • Xuesi Zhou,
  • Yonghong He and
  • Dongmei Li
  • + 3 authors+ 0 author

30 May 2019

Self-reference detection is necessary and important to a biosensor. The linear weak measurement system based on total internal reflection has attracted widespread attention due to its high stability, label-free detection, and easy integration. In thi...

(This article belongs to the Section Biosensors)

of 13