The material I learned from while writing the Computer Vision notes. Each post also lists the original papers behind its content at the end. The Spiking Neural Networks section has its own reference page.
Course
- Computer Vision class by Prof. Dr. Torsten Schön (torsten-schoen.de). The lectures behind this series, covering neural network foundations, CNN architectures from AlexNet to ResNet, efficient CNNs, segmentation, object detection, attention, and Vision Transformers. The posts in this section follow that course, extended with interactive demos, reproduced experiments and references to the original papers.
Books
- Deep Learning: Ian Goodfellow, Yoshua Bengio and Aaron Courville. MIT Press, 2016. Free to read online at deeplearningbook.org. The standard reference for the foundations: linear algebra and probability for machine learning, optimisation, regularisation, convolutional and recurrent networks.
- Computer Vision: Algorithms and Applications (2nd edition): Richard Szeliski. Springer, 2022. Free PDF at szeliski.org/Book. Classical and deep-learning computer vision in one book.
- Understanding Deep Learning: Simon J. D. Prince. MIT Press, 2023. Free PDF and notebooks at udlbook.github.io. A modern, very clearly illustrated introduction, including Transformers and diffusion models.
- Dive into Deep Learning: Aston Zhang, Zachary C. Lipton, Mu Li and Alexander J. Smola. Cambridge University Press, 2023. Free at d2l.ai, with runnable code for every chapter.
Courses online
- Stanford CS231n: Deep Learning for Computer Vision: cs231n.stanford.edu. Lecture notes and assignments on CNNs, detection, segmentation and Transformers.
Tools used in these notes
- PyTorch for every model trained here, and timm for the Vision Transformer weights.
- ONNX Model Zoo and TensorFlow.js models for the pretrained networks that run in the browser.