Deep Learning Algorithms and Practical Research Projects
Buch, Englisch, Format (B × H): 155 mm x 235 mm
ISBN: 978-3-032-46058-5
Verlag: Springer
This book provides a rigorous and current treatment of modern computer vision by linking algorithms with recent advances in artificial intelligence (AI). The book addresses key themes such as representation learning and foundation models, generative and data-centric approaches, and multimodal integration, as well as advanced image processing and embedded vision, while also examining deployment considerations, trustworthiness (explainability and robustness), and evaluation practices. Through real world examples in areas such as medical imaging, environmental remote sensing, robotics, and autonomous systems, and adopting a scientific approach, it balances theoretical insights with practical case studies. Designed for researchers, graduate students, and professionals, this book offers a structured perspective on current algorithms and methods for computer vision.
Zielgruppe
Research
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
Introduction.- Evolving Foundations: From Classical Vision to Modern Paradigms.- Attention-Driven Architectures and Transformer-based Models in Vision.- Self-Supervised and Unsupervised Representation Learning.- Large-Scale Pretraining and Foundation Models for Visual Understanding.- Advanced Detection, Segmentation, and Perception Frameworks.- Temporal Modeling and Video Understanding.- Explainability, Interpretability, and Trust in Vision Systems.- Efficiency and Scalability for Edge, Mobile, and Embedded Scenarios.- Multi-Modal and Cross-Modal Vision Applications.- Generative Vision Models: Synthesis, Editing, and Simulation.- Data Centric Vision: Synthetic Data, Augmentation, and Dataset Curation.- Evaluation, Benchmarking, Reproducibility, and Best Practices.- Ethical, Privacy, and Societal Implications of Modern Vision Systems.- Conclusion.
