Breaking the data barrier: a review of deep learning techniques for democratizing AI with small datasets

IH Rather, S Kumar, AH Gandomi - Artificial Intelligence Review, 2024 - Springer
Justifiably, while big data is the primary interest of research and public discourse, it is
essential to acknowledge that small data remains prevalent. The same technological and …

Development and application of Few-shot learning methods in materials science under data scarcity

Y Chen, P Long, B Liu, Y Wang, J Wang… - Journal of Materials …, 2024 - pubs.rsc.org
Machine learning, as a significant branch of artificial intelligence, has provided effective
guidance for material design by establishing virtual map**s between data and desired …

Structural digital Twin for damage detection of CFRP composites using meta transfer Learning-based approach

C Liu, Y Chen, X Xu - Expert Systems with Applications, 2025 - Elsevier
Using deep learning approaches to identify and locate defects in composite structures made
of Carbon Fiber Reinforced Plastics (CFRP) is becoming increasingly popular. However …

Imperative learning: A self-supervised neural-symbolic learning framework for robot autonomy

C Wang, K Ji, J Geng, Z Ren, T Fu, F Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Data-driven methods such as reinforcement and imitation learning have achieved
remarkable success in robot autonomy. However, their data-centric nature still hinders them …

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

H Lin, N Li, P Yao, K Dong, Y Guo… - … on Circuits and …, 2025 - ieeexplore.ieee.org
Object detection is a fundamental task in computer vision that involves accurately locating
and classifying objects within images or video frames. In remote sensing, this task is …

A comprehensive review of few-shot action recognition

Y Wanyan, X Yang, W Dong, C Xu - arxiv preprint arxiv:2407.14744, 2024 - arxiv.org
Few-shot action recognition aims to address the high cost and impracticality of manually
labeling complex and variable video data in action recognition. It requires accurately …

Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers

M Arbaoui, MA Brahmia, A Rahmoun… - ACM Transactions on …, 2024 - dl.acm.org
The emerging integration of Internet of Things (IoT) and AI has unlocked numerous
opportunities for innovation across diverse industries. However, growing privacy concerns …

IfCMD: A Novel Method for Radar Target Detection under Complex Clutter Backgrounds

C Zhang, Y Xu, W Chen, B Chen, C Gao, H Liu - Remote Sensing, 2024 - mdpi.com
Traditional radar target detectors, which are model-driven, often suffer remarkable
performance degradation in complex clutter environments due to the weakness in modeling …

[HTML][HTML] A Method for Real-Time Lung Nodule Instance Segmentation Using Deep Learning

A Santone, F Mercaldo, L Brunese - Life, 2024 - mdpi.com
Lung screening is really crucial in the early detection and management of masses, with
particular regard to cancer. Studies have shown that lung cancer screening, can reduce lung …

VL-Meta: vision-language models for multimodal meta-learning

H Ma, B Fan, BK Ng, CT Lam - Mathematics, 2024 - mdpi.com
Multimodal learning is a promising area in artificial intelligence (AI) that can make the model
understand different kinds of data. Existing works are trying to re-train a new model based …