Towards Learning Object Detectors With Limited Data For Industrial Applications
Download Towards Learning Object Detectors With Limited Data For Industrial Applications PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Towards Learning Object Detectors With Limited Data For Industrial Applications book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Towards Learning Object Detectors with Limited Data for Industrial Applications
Author: Guirguis, Karim
language: en
Publisher: KIT Scientific Publishing
Release Date: 2025-04-02
In dieser Dissertation werden drei neuartige Generalized FSOD (G-FSOD)-Ansätze vorgestellt, die das Vergessen von zuvor gelernten Klassen beim Lernen neuer Klassen mit begrenzten Daten minimieren. Die ersten beiden Ansätze reduzieren das Vergessen von Basisklassen, wenn diese während des Trainings noch verfügbar sind. Der dritte Ansatz, für Szenarien ohne Basisdaten, nutzt Wissensdestillation, um den Wissenstransfer zu verbessern. - In this dissertation, three novel Generalized Few-Shot Object Detection (G-FSOD) approaches are presented to minimize the forgetting of previously learned classes while learning new classes with limited data. The first two approaches reduce the forgetting of base classes if they are still available during training. The third approach, for scenarios without base data, uses knowledge distillation to improve the knowledge transfer.
Examining the Impact of Deep Learning and IoT on Multi-Industry Applications
Deep learning, as a recent AI technique, has proven itself efficient in solving many real-world problems. Deep learning algorithms are efficient, high performing, and an effective standard for solving these problems. In addition, with IoT, deep learning is in many emerging and developing domains of computer technology. Deep learning algorithms have brought a revolution in computer vision applications by introducing an efficient solution to several image processing-related problems that have long remained unresolved or moderately solved. Various significant IoT technologies in various industries, such as education, health, transportation, and security, combine IoT with deep learning for complex problem solving and the supported interaction between human beings and their surroundings. Examining the Impact of Deep Learning and IoT on Multi-Industry Applications provides insights on how deep learning, together with IoT, impacts various sectors such as healthcare, agriculture, cyber security, and social media analysis applications. The chapters present solutions to various real-world problems using these methods from various researchers’ points of view. While highlighting topics such as medical diagnosis, power consumption, livestock management, security, and social media analysis, this book is ideal for IT specialists, technologists, security analysts, medical practitioners, imaging specialists, diagnosticians, academicians, researchers, industrial experts, scientists, and undergraduate and postgraduate students who are working in the field of computer engineering, electronics, and electrical engineering.
Navigating Challenges of Object Detection Through Cognitive Computing
Cognitive computing is transforming how machines perceive, analyze, and make intelligent decisions, enabling breakthroughs in object detection, segmentation, and image processing. By integrating cognitive algorithms with machine learning, this technology enhances automation, accuracy, and efficiency across industries such as healthcare, finance, and agriculture. The ability of machines to mimic human reasoning opens new frontiers for innovation, leading to smarter diagnostics, risk assessments, and precision-driven solutions. As cognitive computing evolves, its applications will continue to reshape industries, improve decision-making, and drive technological advancements that impact society on a global scale. Navigating Challenges of Object Detection Through Cognitive Computing explores the challenges of object detection across various domains and presents cognitive computing-based intelligent techniques to overcome them. It provides insights into innovative methodologies for improving detection accuracy in complex scenarios such as surface defect detection, indoor environments, adverse weather conditions, UAV imagery, and camouflaged object detection. Covering topics such as smart engineering, social medial sentiment analyses, and healthcare, this book is an excellent resource for computer engineers, computer scientists, industry practitioners, professionals, researchers, scholars, academicians, and more.