Improving the Safety, Reliability, and Efficiency of Cargo Transportation using Deep Learning
Published:
- Multi-class object detection using RetinaNet
- Progress meetings with the industrial partner Streamba
Posts by Collection
applied_research
Automatic Identification of Asbestos Fibres in Air Samples using Deep Learning
Published:
- Instance segmentation using U-Net
- Analysis of fibre size and shape distributions
- Progress meetings with industrial partner Ethos Environmental
Global Wheat Detection (Kaggle Competition)
Published:
- Implementation of various Cut and Mix plus Style Transfer image augmentations
- Single-class object detection using EfficientDet
Predicting AirBnb Prices in Athens using Machine Learning
Published:
- Data Preprocessing
- Feature Engineering
- Regression using Random Forest, XGBoost
Real-time Bolt Detection Using Deep Learning
Published:
- Development of a YOLOv5 deep learning bolt detector
- Real-time bolt detection using ZED 2i camera and Edge AI Gateway
PyTorch IBN-Encoder LSTM-Decoder
Published:
- Encoder-Decoder network architecture combining IBN-Net feature extraction with LSTM sequential modeling.
- Designed for video frame-level prediction, subsea survey annotations, and sequential data analysis.
- Developed during PhD studies to automate pipeline anomaly detection over continuous video frames.
PyTorch Swapping Autoencoder
Published:
- Implementation of Swapping Autoencoders for deep generative representation learning.
- Enables texture and structure manipulation for image-to-image translation tasks.
- Part of PhD research on unsupervised representation learning.
PyTorch Video Dataset Loader & Sampler
Published:
- Efficient dataset loader and sampler helper classes for video classification tasks in PyTorch.
- Optimizes random sampling, clip loading, and preprocessing routines for heavy video data pipelines.
- Used extensively during PhD projects to accelerate model training on subsea survey footage.
Custom Cutout Data Augmentation in PyTorch
Published:
- Implementation of Cutout data regularization/augmentation for convolutional neural networks in PyTorch.
- Provides modular and flexible cutout masks to improve model generalization and robustness against occlusion.
- Developed during PhD studies to enhance data variety for pipeline inspection datasets.
PyTorch 3D IBN-Net
Published:
- 3D Convolutional Neural Network (3D CNN) incorporating Instance-Batch Normalization (IBN-Net) blocks.
- Designed for video spatiotemporal analysis and action recognition with enhanced domain generalization.
- Developed during PhD studies to improve feature extraction robustness under varying subsea conditions.
Panoptic Segmentation with Mask2Former & PyTorch Lightning
Published:
- Training, evaluating, and running inference for Panoptic Segmentation models using Mask2Former.
- Leveraging PyTorch Lightning and Hugging Face Transformers for modular and scalable training pipelines.
- Built during Track32 AI research and development.
WPP Open ResearchLab: Data Quality Assurance Agent
Published:
- Research and development of an intelligent AI agent for automated data quality assurance and schema validation.
- Implementing reasoning-based agents to analyze databases, identify anomalies, and enforce consistency constraints.
- Part of the WPP Open ResearchLab initiative.
cv
publications
Classification of ultrasound images of carotids using Wavelet Transforms and SVM
Published in Diploma Thesis, National Technical University of Athens, 2017
Diploma Thesis implementing SVMs and Wavelet Transforms for medical image classification.
Recommended citation: Stamoulakatos, A. (2017). Classification of ultrasound images of carotids using Wavelet Transforms and SVM (Diploma Thesis, NTUA).
Automatic annotation of subsea pipelines using deep learning
Published in Sensors, MDPI, 2020
Journal publication in Sensors (MDPI) exploring deep learning methodologies for subsea pipeline video survey automated annotations.
Recommended citation: Stamoulakatos, A., Anagnostis, A., & Tachtatzis, C. (2020). Automatic annotation of subsea pipelines using deep learning. Sensors, 20(3), 674. https://doi.org/10.3390/s20030674
A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification
Published in IEEE OCEANS 2021, 2021
Conference paper comparing 2D and 3D CNN architectures for temporal and spatial modeling of underwater pipeline inspection videos.
Recommended citation: Stamoulakatos, A., & Tachtatzis, C. (2021). A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification. In OCEANS 2021 (pp. 1-6). IEEE. https://ieeexplore.ieee.org/document/9706125
Automatic annotation of subsea pipelines using deep learning
Published in PhD Thesis, University of Strathclyde, 2023
Doctoral Thesis exploring the automation of subsea survey video annotations using Deep Learning methodologies.
Recommended citation: Stamoulakatos, A. (2023). Automatic annotation of subsea pipelines using deep learning (Doctoral dissertation, University of Strathclyde). https://strathprints.strath.ac.uk/
talks
teaching
Private Maths/Physics Tutoring
Private Tutoring, , 2015
- Assisted high school students with maths and physics exercises.
C++ Teaching Assistant
Undergraduate Course, University of Strathclyde, EEE Department, 2018
- Assisted 2nd year students in C++ lab exercises and final project
- Taught fundamentals of coding and object oriented programming
Building Your First AI Agent
Educational Repository, GitHub Tutorial / Open Source, 2025
- A beginner-friendly tutorial and code template for building autonomous AI agents.
- Covers agent loop design, tool calling, and prompt engineering fundamentals.
Introduction to AI Agents
Guest Lecture, Athens University of Economics and Business (AUEB), 2026
- Guest lecture on the architecture and development of AI agents.
- Provided practical code examples and hands-on exercises for students.