This repository contains my own solutions to the "Visual Recognition" course at MIMUW. The course focuses on deep learning architectures, implementation techniques, training, and debugging of neural networks for image recognition. Through this course, I have gained theoretical knowledge, insights into contemporary research in the field, and practical skills related to image recognition.
The course covers the following topics:
- Introduction to Image Recognition (Classical methods: SIFT, Hough Transform)
- Convolutional Neural Networks - Review
- Visualization and Interpretability
- Object Detection
- Semantic Segmentation and Instance Segmentation
- Video Understanding
- 3D Vision
- Generative Models
For more details, please refer to the course website.
This course aims to educate students on cutting-edge deep learning architectures for visual recognition, as well as instruct them on implementing, training, and troubleshooting neural networks. It encompasses theoretical knowledge, the latest research findings, and practical skills development.
The repository consists of Jupyter notebooks, scripts, and resources used to solve the course exercises and projects.
- Clone the repository
- Navigate into the repository
- Install required Python packages
- Launch Jupyter Notebook
This repository is for personal academic use. Plagiarism is not encouraged. If you're a student in the "Visual Recognition" course, refrain from copying or using this material for graded assignments. Use this for learning and understanding.