A 5-day hands-on skill enhancement boot camp on

Deep Learning for Object Detection And Semantic Segmentation In Visual Data

Deep Learning and Computer Vision are witnessing tremendous growth over the years due to the application of machine learning algorithms to computer vision tasks such as object recognition and detection, image registration, 3D reconstruction and semantic segmentation. Reaching the full potential of computer vision will be possible once we transition from research labs into the real world. Hence, a five-day workshop on “Object Detection and Semantic Segmentation” is being conducted to drive and assist the journey above. The workshop will help the participants get a deep dive into the underlying architectures and algorithms used for object detection and semantic segmentation and get hands-on experience with the training of deep learning models. Become a part of this exciting workshop and learn about the exciting applications of object detection and semantic segmentation using Deep Learning through enlightening lectures and training classes!


This workshop is designed to empower you to jump-start Computer Vision and learn the hands-on skills and expertise needed to solve the world’s most challenging problems:
  • Understand crucial elements such as object recognition and detection, semantic segmentation, scene understanding, medical image analysis, etc
  • Learn how to build computer vision applications for various healthcare and industrial sectors.
  • Get hands-on experience with the most widely used, industry-standard software, tools, and frameworks through projects.
  • Obtain real-world expertise through content designed by promising faculty members and researchers around the globe.
  • Earn a certificate to demonstrate your subject matter competency and support career growth.

Learning Outcomes

In this workshop series, participants will learn the basics of computer vision by training and deploying deep learning frameworks, as well as building the skill-set and toolbox they need to design their own deep learning solutions through hands-on projects. Participants will”
  • Comprehend Computer Vision jargon.
  • Implement widely used computer vision workflows such as image classification, object detection, semantic segmentation etc.
  • Learn the art of tweaking training parameters to improve accuracy.
  • Learn how to develop CNNs to detect and segment objects from images and videos using Keras/TensorFlow.
  • Learn how to customize the structure of various Convolutional Neural Network (CNN) architectures to adapt to novel problems.
  • Deploy and host trained networks using Flutter.

Who Is This Training For?

  • Recent graduates looking to bolster their skillset.
  • Deep Learning enthusiasts who aim to benefit from current market trends.
  • Data Scientists and researchers who want to solve challenging problems with Computer Vision.
  • Software Engineers looking to boost their careers with the state-of the art Computer Vision expertise.
  • Technology leaders who want to stay ahead in the competition by empowering their organizations with Deep Learning and Computer Vision.
  • Undergraduate students aiming to accomplish their FYPs in the domain of Computer Vision.
Who Is This Training For?


Muhammad Moazam fraz
Dr Muhammad Moazam Fraz

Associate Professor, NUST SEECS, Pakistan

Dr Muhammad Shahzad

Guest Professor, Technical University of Munich (TUM), Germany

Dr Talha Qaiser

Diagnostic Computer Vision Leader, AstraZeneca, United Kingdom


Machine Vision and Intelligent Systems Lab, SEECS NUST

Program Details

Monday, 20 June 2022
Introduction to Deep Learning
  • 10:00 AM – 01:00 PM
    • Fundamentals of Deep Learning
    • Introduction to Deep Learning Model Architectures
    • A gentle introduction to Computer Vision and its applicatio
  • 02:00 PM – 04:00 PM
    • Google Colab configuration and integration with Kaggle
    • Computer Vision models for Image classification, Object Detection in visual data, Scene semantic segmentation
    • Production ready AI (Artificial Intelligence) model development, training & deployment
Tuesday, 21 June 2022
Overview of Object Recognition & Detection
  • 10:00 AM – 01:00 PM
    • An overview of Object Recognition and Detection
    • Object detection frameworks: a contemplative retrospection
    • A gentle introduction of RCNN family
  • 02:00 PM – 04:00 PM
    • Hands-on experience on development of Faster RCNN
    • Training Faster RCNN over several dataset.
    • Real time inference experience of Faster RCNN
Wednesday, 22 June 2022
Overview of Single Shot Detectors
  • 10:00 AM – 01:00 PM
    • Outline limitations with RCNN Family
    • An overview of Single Shot Detectors (SSDs)
    • YOLO Family – the Champions
  • 02:00 PM – 04:00 PM
    • Hands-on on Single Shot Detectors.
    • Training and Deployment of YOLO V3
Thursday, 23 June 2022
Overview of Semantic Segmentation & Scene
  • 10:00 AM – 01:00 PM
    • An overview of Semantic Segmentation & Scene Understanding
    • Classical frameworks for semantic segmentation e.g. FCNs, SegNet, U-Net etc.
  • 02:00 PM – 04:00 PM
    • Hands-on on U-net segmentation framework.
    • Training of U-net over a Medical Imaging dataset
    • Real time inference of U-net over unseen Medical Images
Friday, 24 June 2022
Modern architectures for Semantic
  • 10:00 AM – 01:00 PM
    • Modern architectures for Semantic such as DeepLab Segmentation
    • Overview of applications of Semantic segmentation and Object Detection in healthcare, visual surveillance, motion tracking and precision agriculture
  • 02:00 PM – 04:00 PM
    • Hands-on on object detection and semantic segmentation frameworks over real-world problem.
    • Certificate Distribution Closing Ceremony

Contact Details



Phone Number