[HTML][HTML] Data augmentation: A comprehensive survey of modern approaches

A Mumuni, F Mumuni - Array, 2022‏ - Elsevier
To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

[HTML][HTML] A comprehensive survey of image augmentation techniques for deep learning

M Xu, S Yoon, A Fuentes, DS Park - Pattern Recognition, 2023‏ - Elsevier
Although deep learning has achieved satisfactory performance in computer vision, a large
volume of images is required. However, collecting images is often expensive and …

Smoothllm: Defending large language models against jailbreaking attacks

A Robey, E Wong, H Hassani, GJ Pappas - arxiv preprint arxiv …, 2023‏ - arxiv.org
Despite efforts to align large language models (LLMs) with human intentions, widely-used
LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an …

Self-supervised learning of adversarial example: Towards good generalizations for deepfake detection

L Chen, Y Zhang, Y Song, L Liu… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Recent studies in deepfake detection have yielded promising results when the training and
testing face forgeries are from the same dataset. However, the problem remains challenging …

[HTML][HTML] Automated data processing and feature engineering for deep learning and big data applications: a survey

A Mumuni, F Mumuni - Journal of Information and Intelligence, 2024‏ - Elsevier
Modern approach to artificial intelligence (AI) aims to design algorithms that learn directly
from data. This approach has achieved impressive results and has contributed significantly …

A systematic review on data scarcity problem in deep learning: solution and applications

MA Bansal, DR Sharma, DM Kathuria - ACM Computing Surveys (Csur), 2022‏ - dl.acm.org
Recent advancements in deep learning architecture have increased its utility in real-life
applications. Deep learning models require a large amount of data to train the model. In …

Las-at: adversarial training with learnable attack strategy

X Jia, Y Zhang, B Wu, K Ma… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Adversarial training (AT) is always formulated as a minimax problem, of which the
performance depends on the inner optimization that involves the generation of adversarial …

Semi-supervised and unsupervised deep visual learning: A survey

Y Chen, M Mancini, X Zhu… - IEEE transactions on …, 2022‏ - ieeexplore.ieee.org
State-of-the-art deep learning models are often trained with a large amount of costly labeled
training data. However, requiring exhaustive manual annotations may degrade the model's …

Trivialaugment: Tuning-free yet state-of-the-art data augmentation

SG Müller, F Hutter - Proceedings of the IEEE/CVF …, 2021‏ - openaccess.thecvf.com
Automatic augmentation methods have recently become a crucial pillar for strong model
performance in vision tasks. While existing automatic augmentation methods need to trade …

A comprehensive survey of neural architecture search: Challenges and solutions

P Ren, Y **ao, X Chang, PY Huang, Z Li… - ACM Computing …, 2021‏ - dl.acm.org
Deep learning has made substantial breakthroughs in many fields due to its powerful
automatic representation capabilities. It has been proven that neural architecture design is …