Head of subject: Associate Professor László Czúni
Thematics
Students acquire knowledge related to the following topics, taking into account their individual training plan and interests:
• The concept of machine vision
• Learning and neural mechanisms in biological vision
• Global and local image features
• Detection with Haar Cascades
• Common classification methods: logistic regression, decision trees, SVM
• DNNs and CNNs in recognition and segmentation
• Data annotation and augmentation
• Zero-shot learning and few-shot learning
• Contrastive learning: recommended article
• Adversarial attacks
• Autoencoders
• Attention mechanisms
• Visual transformers
The evaluation is based on the development of an individual project task related to the above topics.
Literature
· Czúni-Tanács: Képi információ mérése, 2011
· Kató-Czúni: Számítógépes látás, 2011
· Ian Goodfellow, Yoshua Bengio, Deep Learning (Adaptive Computation and Machine Learning series), ISBN-13: 978-0262035613, The MIT Press
· Himanshu Singh - Practical Machine Learning and Image Processing For Facial Recognition, Object Detection, and Pattern Recognition Using Python-Apress (2019)
· Mohamed Elgendy - Deep Learning for Vision Systems (2020, Manning Publications)
· Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., ... & Krishnan, D. (2020). Supervised contrastive learning. Advances in neural information processing systems, 33, 18661-18673.
· Rádli, R., & Czúni, L. (2022). Improving the Efficiency of Autoencoders for Visual Defect Detection with Orientation Normalization. In VISIGRAPP (4: VISAPP) (pp. 651-658).
· Akhtar, N., Mian, A., Kardan, N., & Shah, M. (2021). Advances in adversarial attacks and defenses in computer vision: A survey. IEEE Access, 9, 155161-155196.
· Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022). Transformers in vision: A survey. ACM computing surveys (CSUR), 54(10s), 1-41.