Academic Articles & Research Papers

Neural transfer learning for natural language processing

The current generation of neural network-based natural language processing models excels at learning from large amounts of labelled data. Given these capabilities, natural language processing is increasingly applied to new tasks, new domain...

An Analysis of the Training Data Impact for Domain-Adapted Tokenizer Performances—The Case of Serbian Legal Domain Adaptation

Various areas of natural language processing (NLP) have greatly benefited from the development of large language models in recent years. This research addresses the challenge of developing efficient tokenizers for transformer-based domain-s...

Autonomous Driving Roadway Feature Interpretation Using Integrated Semantic Analysis and Domain Adaptation

Lane detection is fundamental to autonomous driving, yet remains challenging in complex environments with occlusions, ambiguous markings, and varied lighting. We introduce the Global Semantic Enhancement Network (GSENet), a groundbreaking f...

Bridging the performance–efficiency gap: a resource-efficient hybrid DL-ML framework for jackfruit disease detection

Complex environment variability and limited computational resources in agricultural settings create challenges in automated detection in tropical regions, where jackfruit diseases pose major threats to harvest productivity and food security...

Domain Adaptation in Computer Vision Applications

Adversarial domain adaptation for false-positive reduction in hospital-to-robotic echocardiographic screening under limited target-domain data.

DAPS3D: Domain Adaptive Projective Segmentation of 3D LiDAR Point Clouds

LiDARs are one of the key sources of reliable environmental ranging information for autonomous vehicles. However, segmentation of 3D scene elements (roads, buildings, people, cars, etc.) based on LiDAR point clouds has limitations. On the o...

Deep learning applications and challenges in big data analytics

Abstract Big Data Analytics and Deep Learning are two high-focus of data science. Big Data has become important as many organizations both public and private have been collecting massive amounts of domain-specific information, which can con...

Deep Learning for the Earth Sciences

Deep learning is a fundamental technique in modern Artificial Intelligence and is being applied to disciplines across the scientific spectrum; earth science is no exception. Yet, the link between deep learning and Earth sciences has only re...

Raman Spectroscopy Pre-Trained Encoder: A Self-Supervised Learning Approach for Data-Efficient Domain-Independent Spectroscopy Analysis

Deep-learning methods have boosted the analytical power of Raman spectroscopy, yet they still require large, task-specific, labeled datasets and often fail to transfer across application domains. The study explores pre-trained encoders as a...