Unveiling roadway hazards: Enhancing fatal crash risk estimation through multiscale satellite imagery and self-supervised cross-matching

G Liang, J Zulu, X Xing, N Jacobs - IEEE Journal of Selected …, 2023 - ieeexplore.ieee.org
Traffic accidents threaten human lives and impose substantial financial burdens annually.
Accurate estimation of accident fatal crash risk is crucial for enhancing road safety and …

Dynamic Label Smoothing and Semantic Transport for Unsupervised Domain Adaptation on Object Recognition

F Ding, J Li, W Tian, S Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The application of domain adaptation techniques has emerged as a valuable approach for
reducing the cost of data annotation in object recognition domains. Despite its usefulness …

Enhancing Neural Text Detector Robustness with μAttacking and RR-Training

G Liang, J Guerrero, F Zheng, I Alsmadi - Electronics, 2023 - mdpi.com
With advanced neural network techniques, language models can generate content that
looks genuinely created by humans. Such advanced progress benefits society in numerous …

Unexplainable explanations: Towards interpreting tSNE and UMAP embeddings

A Draganov, S Dohn - arXiv preprint arXiv:2306.11898, 2023 - arxiv.org
It has become standard to explain neural network latent spaces with attraction/repulsion
dimensionality reduction (ARDR) methods like tSNE and UMAP. This relies on the premise …

CMFAN: Cross-Modal Feature Alignment Network for Few-Shot Single-View 3D Reconstruction

L Lai, J Chen, Z Zhang, G Lin… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Few-shot single-view 3D reconstruction learns to reconstruct the novel category objects
based on a query image and a few support shapes. However, since the query image and the …

Pick up the pace: Fast and simple domain adaptation via ensemble pseudo-labeling

C Liao, T Tsiligkaridis, B Kulis - arXiv preprint arXiv:2205.13508, 2022 - arxiv.org
Domain Adaptation (DA) has received widespread attention from deep learning researchers
in recent years because of its potential to improve test accuracy with out-of-distribution …

A Mutation-based Text Generation for Adversarial Machine Learning Applications

J Guerrero, G Liang, I Alsmadi - arXiv preprint arXiv:2212.11808, 2022 - arxiv.org
Many natural language related applications involve text generation, created by humans or
machines. While in many of those applications machines support humans, yet in few …

Adversarial Text Perturbation Generation and Analysis

J Guerrero, G Liang, I Alsmadi - 2023 3rd Intelligent …, 2023 - ieeexplore.ieee.org
With the evolution of applications of text generations in social networks, the genuineness of
such text is questioned. Machine learning language based models such as GPT now can …

Enhancing Machine Learning Based SQL Injection Detection Using Contextualized Word Embedding

J Zulu, B Han, I Alsmadi, G Liang - Proceedings of the 2024 ACM …, 2024 - dl.acm.org
SQL injection (SQLi) attacks continue to severely threaten application security, allowing
malicious actors to exploit web input and manipulate an application's database with …

Multi-Scale Self-Supervised Consistency Training for Trustworthy Medical Imaging Classification

B Han, C Moran, J Yang, Y Lee, Z Cao… - 2024 46th Annual …, 2024 - ieeexplore.ieee.org
Modern neural network models have demonstrated exceptional classification capabilities
comparable to human performance in various medical diagnosis tasks. However, their …