Deep Learning for Computer Vision: Techniques & Applications

Khalifa University via Coursera

Go to class Write review

Details

Go to class

Provider

Coursera
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Effort

7 weeks, 2 hours a week
Sessions

Self-Paced
Level

Intermediate
Subtitles

English

Found in

Overview

Google, IBM & Meta Certificates – 40% Off

One plan covers every Professional Certificate on Coursera.

Unlock All Certificates

Master modern computer vision through a practical, PyTorch‑first path. In this course you will build, train, and evaluate deep neural networks to solve real‑world image problems. You’ll begin with the end‑to‑end ML workflow and a simple multilayer perceptron (MLP), then learn the core building blocks of convolutional neural networks (CNNs): convolution, pooling, feature maps, and activation functions. From there, you’ll implement and fine‑tune state‑of‑the‑art architectures such as VGG and ResNet, and practice best‑practice model evaluation. You will then tackle object detection and localization with YOLO, SSD, and Faster R‑CNN, and progress to image segmentation with U‑Net and Mask R‑CNN. Along the way you’ll use PyTorch to perform data augmentation, hyperparameter tuning, and non‑maximum suppression while balancing accuracy, speed, and deployment constraints. Designed for learners with basic Python and NumPy, this course is ideal for aspiring machine‑learning engineers, data scientists, and developers who want industry‑ready experience with CNNs, transfer learning, object detection, and image segmentation. Build a portfolio‑quality project and gain in‑demand skills for AI‑powered products. Expect clear code templates and real datasets for practice and reproducible workflows.

Syllabus

Module 1: Introduction to AI, Machine Learning, Computer Vision, and PyTorch

This module introduces the students to Artificial Intelligence (AI) and Machine Learning with a comprehensive overview of the fundamental concepts, theories, and applications of AI and machine learning. Through a combination of theoretical lectures, practical exercises, and real-world examples, students will gain a foundational understanding of AI and its subfield, machine learning.

Module 2: Machine Learning Fundamentals Workflow and MultiLayer Perceptron (MLP)

This module introduces students to Multilayer Perceptron (MLP) and Convolution Neural Network (CNN) Models with a comprehensive understanding of the architecture, training, and applications of MLPs and CNNs in the field of AI and machine learning. Through theoretical lectures, practical exercises, and hands-on implementation, students will gain the necessary knowledge and skills to design, train, and utilize MLP and CNN models for various tasks.

Module 3: Fundamentals of Convolutional Neural Networks (CNNs)

This module introduces the students to advanced topics/techniques in Convolutional Neural Networks (CNN) with an in-depth understanding of advanced techniques and applications in the field of CNNs. Focusing on topics such as transfer learning, layer visualization, and generative models, students will gain the knowledge and skills to leverage the power of CNNs for complex image analysis tasks.

Module 4: Advanced CNN Architectures

This module on Object Detection and Semantic Segmentation using Deep Learning will provide students with a comprehensive understanding of advanced techniques for detecting objects and performing pixel-level segmentation in images and videos. Through a combination of theoretical lectures, practical exercises, and hands-on projects, students will gain the necessary knowledge and skills to effectively tackle complex computer vision tasks using deep learning methods.

Module 5: Object Detection and Localization

This module on Deep Learning for Computer Vision with PyTorch provides students with a comprehensive understanding of using the PyTorch framework to solve various computer vision tasks. Through a combination of hands-on exercises, and practical projects, students will gain the necessary knowledge and skills to effectively tackle classification, generative modeling, object detection, and image segmentation tasks using deep learning techniques.

Module 6: Image Segmentation

This module on Image Segmentation provides students with a comprehensive understanding of advanced techniques for segmenting and analyzing images using deep learning methods. Students will gain the necessary knowledge and skills to build, train, and evaluate image segmentation models for a range of computer vision applications.

Capstone Project: Real-world Application with PyTorch

This module serves as a culminating experience in which students will apply concepts and techniques from across the course in a practical computer vision context. Through project-based work and applied problem-solving, students will further develop their understanding of deep learning with PyTorch while demonstrating their ability to approach real-world computer vision tasks.