CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community

Y Liu, B Guo, N Li, Y Ding, Z Zhang… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of
Internet of Things (IoT) and Artificial Intelligence (AI) technologies. The fundamental goal of …

Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Approach for Object Detection

T Kim, E Lin, J Lee, C Lau… - Advances in Neural …, 2024 - proceedings.neurips.cc
Federated Learning (FL) has emerged as a potent framework for training models across
distributed data sources while maintaining data privacy. Nevertheless, it faces challenges …

[HTML][HTML] Semi-supervised object detection with uncurated unlabeled data for remote sensing images

N Liu, X Xu, Y Gao, Y Zhao, HC Li - International Journal of Applied Earth …, 2024 - Elsevier
Annotating remote sensing images (RSIs) poses a significant challenge, primarily due to its
labor-intensive nature. Semi-supervised object detection (SSOD) methods address this …

Expert teacher based on foundation image segmentation model for object detection in aerial images

Y Yu, X Sun, Q Cheng - Scientific Reports, 2023 - nature.com
Despite the remarkable progress of general object detection, the lack of labeled aerial
images limits the robustness and generalization of the detector. Teacher–student learning is …

A universal traffic sign detection system using a novel self-training neural network modeling approach

AJC Trappey, OTC Shen - Advanced Engineering Informatics, 2024 - Elsevier
As the development of self-driving (autonomous) vehicles is getting matured and ready for
the road, there is a growing concern regarding their safety performance among the general …

Remote Sensing Teacher: Cross-Domain Detection Transformer with Learnable Frequency-Enhanced Feature Alignment in Remote Sensing Imagery

J Han, W Yang, Y Wang, L Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) is critical for remote sensing object detection in real
applications, aiming to address the significant performance degradation issue caused by the …

ESD-YOLOv5: A Full-Surface Defect Detection Network for Bearing Collars

J Li, H Pan, J Li - Electronics, 2023 - mdpi.com
To address the different forms and sizes of bearing collar surface defects, uneven
distribution of defect positions, and complex backgrounds, we propose ESD-YOLOv5, an …

Data Matters: Rethinking the Data Distribution in Semi-Supervised Oriented SAR Ship Detection

Y Yang, P Lang, J Yin, Y He, J Yang - Remote Sensing, 2024 - search.proquest.com
Data, in deep learning (DL), are crucial to detect ships in synthetic aperture radar (SAR)
images. However, SAR image annotation limitations hinder DL-based SAR ship detection. A …

[HTML][HTML] Unsupervised selective labeling for semi-supervised industrial defect detection

J Ge, Q Qin, S Song, J Jiang, Z Shen - Journal of King Saud University …, 2024 - Elsevier
In industrial detection scenarios, achieving high accuracy typically relies on extensive
labeled datasets, which are costly and time-consuming. This has motivated a shift towards …

Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection

S Zeng, W Zheng, J Lu, H Yan - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
3D object detection aims to recover the 3D information of concerning objects and serves as
the fundamental task of autonomous driving perception. Its performance greatly depends on …