Course10610622464 lectures
Deep Learning for Computer Vision
Prof. Vineeth N Balasubramanian · IIT Hyderabad
About
The automatic analysis and understanding of images and videos, a field called Computer Vision, occupies significant importance in applications including security, healthcare, entertainment, mobility, etc. The recent success of deep learning methods has revolutionized the field of computer vision, making new developments increasingly closer to deployment that benefits end users. This course will introduce the students briefly to traditional computer vision topics, before presenting deep learning methods for computer vision. This course delves into the fundamental concepts of neural networks, explores convolutional architectures, and covers the latest advancements in computer vision tasks such as image classification, object detection, segmentation, and generative modeling. Students will engage in hands-on programming assignments, as well as learn to implement and optimize deep learning models. By the end of the course, participants will be equipped with the skills and knowledge to contribute to the rapidly evolving field of computer vision, pushing the boundaries of what machines can perceive and understand.
The course assumes a basic background in machine learning, and may be most useful to students that have also completed basic introductory materials on deep learning.
INTENDED AUDIENCE : Senior undergraduate students, Post-graduate students, Industry professionals seeking to understand computer vision
Prerequisites: Completion of a basic course in Machine Learning(Recommended, not mandatory) Completion of a course in Deep Learning, or exposure to topics in neural networksKnowledge of basics in probability, linear algebra, and calculusExperience of programming in PythonIf you are unsure whether you meet the background requirements for the course, please look at Assignment 0 (both theory and programming). If you are comfortable solving/following these assignments, you are ready for the course.
Lectures
Week 1
- Course Introduction
- History
- [Optional] Image Formation
- Image Representation
- Linear Filtering
- Image in Frequency Domain
- [Optional] Image Sampling
Week 2
- Edge Detection
- From Edges to Blobs and Corners
- Scale Space, Image Pyramids and Filter Banks
- Feature Detectors : SIFT and Variants
- [Optional] Image Segmentation
- Other Feature Spaces
- [Optional] Human Visual System
Week 3
- Neural Networks: A Review - Part 1
- Neural Networks: A Review - Part 2
- Feedforward Neural Networks and Backpropagation - Part 1
- Feedforward Neural Networks and Backpropagation - Part 2
- Gradient Descent and Variants - Part 1
- Gradient Descent and Variants - Part 2
- Regularization in Neural Networks - Part 1
- Regularization in Neural Networks - Part 2
- Improving Training of Neural Networks - Part 1
- Improving Training of Neural Networks - Part 2
Week 4
- Convolutional Neural Networks: An Introduction - Part 01
- Convolutional Neural Networks: An Introduction - Part 02
- Backpropagation in CNNs
- CNN Architectures for Image Classification: AlexNet, VGG
Week 5
- Evolution of CNN Architectures: InceptionNet, ResNet
- Newer and Recent CNN Architectures
- Finetuning CNNs
- Visualizing CNNs
Week 6
- CNNs for Object Detection: Pre-Deep Learning Era and Initial Steps
- CNNs for Object Detection: Two-Stage Models
- CNNs for Object Detection: Single-stage Models
- CNNs for Segmentation
Week 7
- Recurrent Neural Networks: Introduction
- Backpropagation in RNNs
- LSTMs and GRUs
- Video Understanding using CNNs and RNNs
Week 8
- Attention in Vision Models: An Introduction
- Soft and Hard Attention: Image Captioning
- Additional Content: Beyond Captioning: Visual QA and Dialog
- Self-Attention and Transformers
Week 9
Week 10
- Deep Generative Models: An Introduction
- Generative Adversarial Networks - Part 1
- Generative Adversarial Networks - Part 2
- GAN Hacks and Improvements
- Variational Autoencoders
- VAEs and Disentanglement
Week 11
- Introduction to Diffusion Models and DDPMs - Part 1
- Introduction to Diffusion Models and DDPMs - Part 2
- Classifier and Classifier-Free Diffusion Guidance
Week 12
- Contrastive Learning and History in Face Understanding - Part 1
- Contrastive Learning and History in Face Understanding - Part 2
- Self-Supervised Learning: SimCLR
- Vision Language Models: Introduction and History
- CLIP: The Anchoring Inflection Point
- Beyond CLIP: BLIP, BLIP-2 and CoCA
- From VLMs to Multimodal LLMs
- Course Conclusion
Syllabus and materials
At NPTEL, as the course publishes them.
Credits and licence
- Institution
- IIT Hyderabad
- Department
- Computer Science and Engineering
- Teacher
- Prof. Vineeth N Balasubramanian
- Level
- Undergraduate
- Language
- English
- Subjects
- Computer science, Engineering
- Source
- NPTEL
- Licence
- CC BY-NC-SA, as NPTEL states it. Non-commercial use only. NPTEL's terms
- Attribution
- NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge. Coordinated by IIT Madras.
- Who can watch
- NPTEL gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed